© 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. 196480
    Prev
    Next
    INDEX
    Explanations

    addresses and locations

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

    Growth Mindset

    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
     列
    0.60
    ex
    0.55
     優
    0.54
     ಬಹಳ
    0.51
     Дан
    0.50
    equiv
    0.50
    vee
    0.50
     非常
    0.50
     До
    0.46
    h
    0.46
    POSITIVE LOGITS
    وریت
    0.47
    getNum
    0.46
    ך
    0.46
    ρίες
    0.44
     autonom
    0.44
    TextureData
    0.43
    ţia
    0.43
     dragons
    0.42
    子が
    0.42
     رباع
    0.41
    Activations Density 0.000%

    No Known Activations