© 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. 48000
    Prev
    Next
    INDEX
    Explanations

    names, brands, or actions

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

    specific destinations and identification

    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
     tin
    0.50
    breaker
    0.48
     Finn
    0.47
    ين
    0.44
     keen
    0.44
    -
    0.43
    pane
    0.43
     pê
    0.43
    burse
    0.43
    நு
    0.42
    POSITIVE LOGITS
    酸化
    0.45
    ("/{
    0.45
    スムーズ
    0.45
     Smo
    0.45
    댐
    0.45
     prays
    0.44
     repe
    0.43
     reconc
    0.43
    SampleSize
    0.42
    パーク
    0.42
    Activations Density 0.000%

    No Known Activations