© 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. 182293
    Prev
    Next
    INDEX
    Explanations

    feeling followed by a state or entity

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

    acknowledging user situation

    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
    تی
    0.52
    Cidade
    0.48
    도
    0.47
    脸上
    0.46
     لإ
    0.45
     في
    0.44
    بی
    0.44
    abis
    0.43
    सु
    0.43
     عندي
    0.42
    POSITIVE LOGITS
    直し
    0.44
     agentes
    0.43
     redesigned
    0.43
    まさに
    0.43
    を超
    0.42
     simplices
    0.42
    AssignableFrom
    0.42
    IsResolver
    0.41
     '*.
    0.41
     crainte
    0.41
    Activations Density 0.000%

    No Known Activations