© 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. 50979
    Prev
    Next
    INDEX
    Explanations

    million in users

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

    control and restrictions

    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
    ח
    0.52
    ק
    0.46
    琇
    0.43
    ד
    0.43
    ุม
    0.42
    ש
    0.41
    也要
    0.40
    שי
    0.40
    ility
    0.40
    फ
    0.39
    POSITIVE LOGITS
     ਪਰ
    0.48
    ありました
    0.48
     Anglican
    0.45
     Inquisition
    0.45
    ありますが
    0.44
     入っ
    0.44
    gag
    0.43
    ãos
    0.42
     Catedral
    0.42
     effett
    0.42
    Activations Density 0.000%

    No Known Activations