© 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. 14597
    Prev
    Next
    INDEX
    Explanations

    score and overall

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

    win-loss records

    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
    রোধ
    0.46
     ቀን
    0.40
     ደቂ
    0.40
     fewest
    0.39
    >−</
    0.39
     পরিশোধ
    0.39
    źdz
    0.39
    कर्षण
    0.39
    !');
    0.39
    ⏱
    0.39
    POSITIVE LOGITS
     Collegiate
    0.47
     AMC
    0.45
    いております
    0.44
     Meld
    0.43
     Meet
    0.43
     Maur
    0.42
     Medi
    0.42
     Medical
    0.42
     Mysteries
    0.42
     Acad
    0.41
    Activations Density 0.039%

    No Known Activations