© 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. 73821
    Prev
    Next
    INDEX
    Explanations

    see also

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

    see also below

    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
     sogar
    0.44
     کوي
    0.44
    াড়া
    0.43
    प्लीट
    0.43
    %).
    0.42
     Amin
    0.42
    حبه
    0.42
     زیرمه
    0.42
    টুকু
    0.41
    microseconds
    0.40
    POSITIVE LOGITS
    ла
    0.47
     ecclesiastical
    0.46
    ל
    0.46
    関連項目
    0.46
    orphism
    0.43
    Un
    0.43
    ან
    0.43
     rite
    0.42
     ,
    0.42
    ية
    0.41
    Activations Density 0.001%

    No Known Activations