© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 40284
    Prev
    Next
    INDEX
    Explanations

    terrestrial communication or alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     partly
    0.50
     partially
    0.45
    ння
    0.44
    ن
    0.44
    ي
    0.44
     R
    0.44
    $\$
    0.44
     salvo
    0.43
     Safran
    0.43
    Ҫ
    0.43
    POSITIVE LOGITS
     池
    0.50
    aprendizaje
    0.47
     ไหร่
    0.45
     haremos
    0.45
     ধাঁ
    0.44
    aap
    0.44
    deque
    0.44
    pá
    0.44
    ឹង
    0.43
    യിലേ
    0.43
    Activations Density 0.002%

    No Known Activations