© 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. 65091
    Prev
    Next
    INDEX
    Explanations

    directions and models

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

    affects or describes causes

    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
     おしゃれ
    0.52
    >©
    0.47
    u
    0.46
    ポンプ
    0.46
    concepto
    0.46
    ció
    0.45
    bones
    0.45
    ’?
    0.44
    patri
    0.43
    ревнова
    0.43
    POSITIVE LOGITS
     vur
    0.51
    ت
    0.46
     ज़रूरत
    0.45
     ATTOR
    0.45
     Gorb
    0.45
    ું
    0.45
     DISEASE
    0.45
     wx
    0.44
     XHTML
    0.44
    ਨੇ
    0.44
    Activations Density 0.000%

    No Known Activations