© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 211116
    Prev
    Next
    INDEX
    Explanations

    have adequate

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

    asking why or for reminders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    te
    0.54
    is
    0.49
    ar
    0.49
    po
    0.48
    }
    0.48
    pepper
    0.48
    commit
    0.46
    amor
    0.45
    il
    0.45
    mol
    0.45
    POSITIVE LOGITS
     ثلاث
    0.53
     εισ
    0.53
    oleč
    0.52
     संपादित
    0.50
     चेक
    0.49
    <unused65>
    0.48
    VCTarget
    0.48
     buzzer
    0.48
    DeleteDialogOpen
    0.48
    <unused59>
    0.47
    Activations Density 0.000%

    No Known Activations