© 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. 203074
    Prev
    Next
    INDEX
    Explanations

    leave early

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

    question marksproject?

    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
    وتي
    0.58
    خت
    0.50
    اسي
    0.50
    ويت
    0.48
    ست
    0.47
    ви
    0.46
    Appointment
    0.45
    ১
    0.45
    数
    0.44
    叹
    0.44
    POSITIVE LOGITS
     Intelig
    0.53
     reproduc
    0.48
     Contempor
    0.48
     menace
    0.47
     apropri
    0.47
     ورژن
    0.46
     personagens
    0.46
     morphologies
    0.45
     homogene
    0.45
     mengerjakan
    0.45
    Activations Density 0.001%

    No Known Activations