© 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. 4657
    Prev
    Next
    INDEX
    Explanations

    items described with adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    тре
    0.54
     milhões
    0.52
     аны
    0.48
    ру
    0.47
    }$
    0.47
    рен
    0.46
    лен
    0.45
    猀
    0.45
     obligado
    0.45
    тическая
    0.44
    POSITIVE LOGITS
    four
    0.53
     eatery
    0.49
    pointing
    0.48
    goal
    0.47
    inthe
    0.46
    ‼
    0.45
    sp
    0.45
    ARM
    0.45
    fight
    0.44
    Synchron
    0.44
    Activations Density 0.001%

    No Known Activations