© 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. 9422
    Prev
    Next
    INDEX
    Explanations

    explanation follows factual statements

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

    open-weights AI assistant

    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
     destinés
    0.36
     কাপড়
    0.35
    第壹百
    0.35
     gonflement
    0.34
     craindre
    0.34
    琙
    0.33
     threx
    0.33
    <unused2183>
    0.32
    孅
    0.32
     اقصیٰ
    0.32
    POSITIVE LOGITS
    1
    0.47
     I
    0.44
    :
    0.44
    6
    0.44
    0.44
    3
    0.44
    2
    0.42
    8
    0.42
    7
    0.42
    y
    0.41
    Activations Density 0.065%

    No Known Activations