© 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. 25047
    Prev
    Next
    INDEX
    Explanations

    experienced in demonstrated history

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

    industrial base or US stocks

    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
     আন
    0.41
    控股
    0.37
    쨍
    0.37
     GmbH
    0.37
     הש
    0.36
    还没
    0.35
    淘汰
    0.35
     非
    0.35
     לאחר
    0.35
    延長
    0.35
    POSITIVE LOGITS
    मैं
    0.45
     मैने
    0.44
    fieldset
    0.38
     ഞാൻ
    0.38
     ሽፋ
    0.38
    ியுள்ள
    0.37
    녈
    0.37
    लाइ
    0.37
    Мне
    0.37
     interesado
    0.36
    Activations Density 0.000%

    No Known Activations