© 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. 181082
    Prev
    Next
    INDEX
    Explanations

    legal and technical terms

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

    planning and strategy

    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
    ани
    0.49
    💏
    0.46
    Й
    0.46
    िनी
    0.45
    ऋ
    0.45
    ujo
    0.45
    remeno
    0.45
    ९
    0.44
    𝗩
    0.44
    वायु
    0.43
    POSITIVE LOGITS
     moulds
    0.47
     quirks
    0.45
     jargon
    0.43
     systolic
    0.41
     GDPR
    0.40
     onerous
    0.40
     proteolytic
    0.40
    শরীর
    0.40
    ekar
    0.40
     Wimbledon
    0.40
    Activations Density 0.000%

    No Known Activations