© 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. 161191
    Prev
    Next
    INDEX
    Explanations

    generation of iOS

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

    export through

    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
    pall
    0.46
    szág
    0.46
    ürich
    0.46
     సి
    0.45
    dí
    0.45
     économ
    0.45
     (−
    0.45
     Ayo
    0.45
     (
    0.44
    Pall
    0.44
    POSITIVE LOGITS
     forno
    0.46
    ﺏ
    0.43
    ്യാപ
    0.42
     Шу
    0.42
    כז
    0.42
    他にも
    0.41
    setTimeout
    0.41
    removeAttribute
    0.41
     sostegno
    0.41
    াক্তন
    0.40
    Activations Density 0.001%

    No Known Activations