© 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. 16620
    Prev
    Next
    INDEX
    Explanations

    university, college, villa accommodation

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

    programming languages and technical terms

    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
    iktok
    0.42
    𝗶
    0.38
    id
    0.38
    ol
    0.36
    og
    0.36
    ırs
    0.36
    ק
    0.36
    ги
    0.36
    en
    0.35
    ors
    0.35
    POSITIVE LOGITS
     aunque
    0.36
     diez
    0.34
     mitologia
    0.34
     Reine
    0.33
     meski
    0.33
     segundo
    0.33
     (=
    0.32
     (
    0.32
     magia
    0.32
     mengaku
    0.32
    Activations Density 0.025%

    No Known Activations