© 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. 8825
    Prev
    Next
    INDEX
    Explanations

    singled to base or up

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

    UI elements and graphics

    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
     végétation
    0.51
    赧
    0.46
    เทศ
    0.46
    ധ്യ
    0.45
     difíc
    0.44
    dicke
    0.44
    रिपोर्ट
    0.43
    𒈪
    0.43
    لمات
    0.42
     ആദ്യം
    0.42
    POSITIVE LOGITS
     with
    0.52
     με
    0.49
     on
    0.48
     type
    0.47
     from
    0.45
     với
    0.43
    ↵
    0.40
     Panama
    0.40
     ,
    0.40
     LED
    0.40
    Activations Density 0.007%

    No Known Activations