© 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. 75292
    Prev
    Next
    INDEX
    Explanations

    subtle prompts and deliberate requests

    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
    發現
    0.48
    tted
    0.46
    গতকাল
    0.46
    发现
    0.46
    sma
    0.45
    დაც
    0.45
    発見
    0.45
    Τ
    0.44
    事故
    0.44
     akik
    0.44
    POSITIVE LOGITS
    getElementsBy
    0.43
     смотри
    0.43
     listener
    0.42
     complet
    0.41
     newcomer
    0.41
     biographer
    0.41
    newUser
    0.40
    kinson
    0.40
    estrian
    0.39
     library
    0.38
    Activations Density 0.001%

    No Known Activations