© 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. 236103
    Prev
    Next
    INDEX
    Explanations

    Substitution followed by team name

    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
     outta
    0.49
     între
    0.48
    סת
    0.47
     détermine
    0.47
    ħ
    0.43
    ִ
    0.43
    و
    0.42
     accél
    0.42
    on
    0.41
    ฟรี
    0.41
    POSITIVE LOGITS
     美術
    0.48
     代
    0.48
    fileName
    0.45
     данного
    0.43
     lender
    0.43
    orderLine
    0.43
     یہودی
    0.42
     detained
    0.41
     生地
    0.41
     ಔಷ
    0.41
    Activations Density 0.000%

    No Known Activations