© 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. 233710
    Prev
    Next
    INDEX
    Explanations

    loan banks and issues

    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
     Sociology
    0.54
     मोनालिसा
    0.46
     możli
    0.46
     taget
    0.46
     Saraj
    0.45
     کرده
    0.45
     Muit
    0.44
    逖
    0.43
    鵃
    0.43
     შესაძ
    0.42
    POSITIVE LOGITS
    按钮
    0.44
    于
    0.42
    阿
    0.42
    小
    0.40
    PushButton
    0.40
    的路
    0.40
    BSCRIBE
    0.39
    Button
    0.39
    Caps
    0.39
    Aim
    0.39
    Activations Density 0.004%

    No Known Activations