© 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. 7121
    Prev
    Next
    INDEX
    Explanations

    states and achievements

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

    neglecting responsibilities

    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
    <unused41>
    0.44
     voiture
    0.43
     cré
    0.41
     Slave
    0.40
    轴
    0.39
    用于
    0.39
    服务
    0.38
    综合
    0.38
    创
    0.38
     hòa
    0.37
    POSITIVE LOGITS
    squirrel
    0.47
    郵便
    0.45
     reput
    0.44
    🐢
    0.44
     منظم
    0.41
     karşınız
    0.40
    mnu
    0.40
    theory
    0.40
     ਕੀ
    0.40
    mut
    0.39
    Activations Density 0.000%

    No Known Activations