© 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. 228894
    Prev
    Next
    INDEX
    Explanations

    security interests

    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
     ներ
    0.49
     ಕಾರಣ
    0.48
     sentirse
    0.48
     আচ
    0.47
    𒌨
    0.47
     जरा
    0.46
     genü
    0.45
    тувати
    0.45
     외부
    0.45
     spaceleft
    0.45
    POSITIVE LOGITS
    .
    0.55
    <0xCD>
    0.49
     diligence
    0.49
    \
    0.49
    <h2>
    0.47
     +
    0.46
    .+
    0.46
    X
    0.45
    ;)
    0.45
    ,
    0.44
    Activations Density 0.001%

    No Known Activations