© 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. 168106
    Prev
    Next
    INDEX
    Explanations

    resist scratches, storing craft, moves mountains

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

    extend functionality, violate rights

    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
    m
    0.52
     initiation
    0.51
     harbors
    0.50
    ir
    0.50
     fixation
    0.49
     corners
    0.48
     linings
    0.48
     activation
    0.47
     harboring
    0.47
     M
    0.47
    POSITIVE LOGITS
    瑉
    0.50
     Гуляць
    0.48
    čki
    0.47
    槁
    0.46
    酽
    0.46
     влияет
    0.46
     همیشه
    0.46
     Боли
    0.46
    وقع
    0.45
     சதவீ
    0.45
    Activations Density 0.002%

    No Known Activations