© 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. 74170
    Prev
    Next
    INDEX
    Explanations

    web properties Crimson Fort demo materials protein level

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

    bordering, individuals, quality

    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
     immersion
    0.48
     planar
    0.45
     หลาย
    0.44
     밝혔
    0.44
     isopropyl
    0.44
     ት
    0.44
     grove
    0.44
     ruimte
    0.43
     첫
    0.43
     Fairy
    0.43
    POSITIVE LOGITS
    secrets
    0.58
    ку
    0.55
    proteins
    0.55
    protein
    0.52
    會
    0.51
    prosperity
    0.51
    radas
    0.50
    Hence
    0.50
    SELL
    0.50
    就會
    0.49
    Activations Density 0.015%

    No Known Activations