© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 579
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

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

    options for marketing or business

    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_53_width_65k_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
    <unused2171>
    0.50
     byli
    0.44
     sentenced
    0.44
     besondere
    0.43
     guiclass
    0.43
     tuvieron
    0.43
     ঢুকে
    0.43
    <unused2121>
    0.43
     modalités
    0.43
     জনসাধারণ
    0.42
    POSITIVE LOGITS
    ￥
    0.58
     WIFI
    0.55
    Kana
    0.53
    உங்கள்
    0.52
                            
    0.52
    接着
    0.50
    Google
    0.49
    Balance
    0.49
    Data
    0.49
    Debugging
    0.49
    Activations Density 0.000%

    No Known Activations