© 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. 189037
    Prev
    Next
    INDEX
    Explanations

    claim establishes

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

    feathers or

    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
    ما
    0.50
    ﾒ
    0.48
     ним
    0.47
    Shannon
    0.45
    门
    0.44
    פי
    0.44
    జీ
    0.44
    룸
    0.44
    مر
    0.43
    зап
    0.43
    POSITIVE LOGITS
     Neues
    0.52
     Represent
    0.51
     respiratoires
    0.50
     Estable
    0.47
     पाएं
    0.46
     WITH
    0.46
     Gottes
    0.46
     Teg
    0.45
     Preferably
    0.45
     मल्टीप्लाई
    0.44
    Activations Density 0.000%

    No Known Activations