© 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. 201025
    Prev
    Next
    INDEX
    Explanations

    required, latest, posted, consequences

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

    child, current, absent, funding, csv

    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
     działal
    0.48
    ையினர்
    0.48
     impe
    0.45
    ержа
    0.45
     dépos
    0.42
     comunità
    0.41
    ]}{\
    0.41
     działalności
    0.41
     contaminating
    0.41
     permas
    0.41
    POSITIVE LOGITS
    atrical
    0.56
     एक्स
    0.54
    ي
    0.52
    i
    0.51
     продол
    0.50
     Paralym
    0.50
     Ци
    0.50
    arif
    0.50
    utsu
    0.48
     ܥ
    0.48
    Activations Density 0.001%

    No Known Activations