© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 204529
    Prev
    Next
    INDEX
    Explanations

    security, systems, and transactions

    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
    Mother
    0.51
     основ
    0.49
    तील
    0.45
    కు
    0.44
    부
    0.43
    만
    0.43
    Parent
    0.42
    แน
    0.42
    Основ
    0.42
     дире
    0.41
    POSITIVE LOGITS
     você
    0.46
     Sulawesi
    0.44
    logs
    0.44
    🚓
    0.44
     നിങ്ങൾക്ക്
    0.43
     logics
    0.42
     yoki
    0.42
     faulty
    0.42
    ¢
    0.42
     addirittura
    0.41
    Activations Density 0.006%

    No Known Activations