© 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. 95554
    Prev
    Next
    INDEX
    Explanations

    savings and apply

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

    language capabilities and doubts

    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
     failed
    0.48
    หมู่
    0.46
    소가
    0.45
    гада
    0.43
     faulty
    0.42
    ༞
    0.42
    ту
    0.42
     વૃ
    0.41
    мага
    0.41
    인이
    0.39
    POSITIVE LOGITS
    都會
    0.52
    iek
    0.48
    motiv
    0.47
    buat
    0.46
    Will
    0.46
     vse
    0.45
     basiert
    0.45
     aumentare
    0.44
    ount
    0.44
     seront
    0.44
    Activations Density 0.004%

    No Known Activations