© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 110270
    Prev
    Next
    INDEX
    Explanations

    expressing choice or preference

    np_acts-logits-general · gemini-2.5-flash-lite

    sentences where the speaker (the model) asserts a personal choice, opinion, or first-person decision (e.g., "I would..." / "I'd ...").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     marker
    0.42
     sedang
    0.42
     symmetrically
    0.39
    既然
    0.38
     Bord
    0.38
     -(
    0.37
     joten
    0.37
     frequent
    0.36
     synonymous
    0.36
     -
    0.36
    POSITIVE LOGITS
    would
    0.67
     gladly
    0.64
     любого
    0.61
     Prefer
    0.61
     würden
    0.59
     bárm
    0.59
     sarebbero
    0.59
     prefer
    0.57
     любом
    0.57
     zouden
    0.57
    Activations Density 0.039%

    No Known Activations