© 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. 155841
    Prev
    Next
    INDEX
    Explanations

    Choose anything or vote

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

    niche or disclosure

    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
     انڈیا
    0.51
     الان
    0.50
     مد
    0.47
     변
    0.47
     ميد
    0.46
     ایم
    0.46
    mapSize
    0.46
     확장
    0.46
     پلا
    0.46
    riya
    0.45
    POSITIVE LOGITS
     lotions
    0.47
    ^{(\
    0.43
     aquilo
    0.43
     interfer
    0.42
     முடியாத
    0.42
     Stok
    0.42
     eyepiece
    0.41
     Asthma
    0.41
     Pantone
    0.41
     Слу
    0.40
    Activations Density 0.004%

    No Known Activations