© 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. 100395
    Prev
    Next
    INDEX
    Explanations

    following chart; root cause

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

    actions and connections

    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
    Ｅ
    0.54
    蹦
    0.49
    ੇ
    0.47
    ერ
    0.46
    ით
    0.45
    ［
    0.45
    мены
    0.44
    決
    0.44
    佐
    0.44
    تباين
    0.44
    POSITIVE LOGITS
     costruzione
    0.50
     গৃহে
    0.49
     எப்போதும்
    0.49
     cherish
    0.48
     imó
    0.48
     slat
    0.48
     innen
    0.46
    षण
    0.46
     occupy
    0.46
     transparencia
    0.46
    Activations Density 0.000%

    No Known Activations