© 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. 125419
    Prev
    Next
    INDEX
    Explanations

    equivalent to

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

    analogous, related, or equivalent to

    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
    ev
    0.56
     Attractive
    0.46
    attractive
    0.45
    ank
    0.44
    会社の
    0.44
    ो
    0.43
    soluble
    0.43
    าส
    0.43
    does
    0.42
     आकर्षक
    0.42
    POSITIVE LOGITS
    ㄍ
    0.50
     দুর্দ
    0.47
     চে
    0.45
     degli
    0.45
     accad
    0.45
     prostředí
    0.45
     протягом
    0.44
    段时间
    0.43
     ders
    0.42
    leşt
    0.42
    Activations Density 0.000%

    No Known Activations