© 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. 232823
    Prev
    Next
    INDEX
    Explanations

    projects generate rubbish

    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
    .~\
    0.49
    ہد
    0.48
    াদী
    0.48
     რომელიც
    0.48
    пределение
    0.46
     mengaj
    0.46
    בד
    0.45
    ริญ
    0.45
    炡
    0.44
    垁
    0.44
    POSITIVE LOGITS
    ullan
    0.50
     национа
    0.47
     technische
    0.47
     nutri
    0.44
     وكان
    0.44
     entsprechend
    0.44
    pei
    0.43
     fünf
    0.43
     waż
    0.43
     summits
    0.43
    Activations Density 0.000%

    No Known Activations