© 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. 73939
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases

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

    connections, adherence, impact, volume

    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
    us
    0.52
    wf
    0.46
    м
    0.46
    ud
    0.44
    hud
    0.44
    DP
    0.44
    f
    0.44
    udad
    0.44
    rit
    0.43
    ader
    0.43
    POSITIVE LOGITS
     रोकता
    0.54
     μαγγ
    0.49
     ἡ
    0.47
     softness
    0.47
     dull
    0.47
     бывают
    0.47
     keď
    0.46
     δύ
    0.46
     RANDOM
    0.46
     substitu
    0.46
    Activations Density 0.000%

    No Known Activations