© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 13182
    Prev
    Next
    INDEX
    Explanations

    muted status

    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
     Leiter
    0.41
     demuestra
    0.38
    Plaintiff
    0.38
    Przeczytaj
    0.37
    Yours
    0.37
     consulté
    0.37
    ႏ
    0.37
    RENDER
    0.36
    係
    0.36
     đào
    0.35
    POSITIVE LOGITS
     larges
    0.38
     multiport
    0.37
     canyon
    0.37
     somewhat
    0.36
     나머
    0.36
     flicker
    0.35
    রিষ্ঠ
    0.35
     hanging
    0.34
    ម្លៃ
    0.34
     многи
    0.34
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.