© 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. 28981
    Prev
    Next
    INDEX
    Explanations

    other wired security solutions

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

    code blocks in programming

    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
     Lattice
    0.53
    ferm
    0.43
     Latex
    0.43
    cardia
    0.42
     Environment
    0.42
    .”.
    0.42
     Latino
    0.42
     *);
    0.41
    default
    0.40
     Latte
    0.40
    POSITIVE LOGITS
     travaillé
    0.48
     चार्
    0.46
     avantages
    0.44
     connues
    0.43
    vény
    0.42
    getBlueTeam
    0.42
     tib
    0.40
    TUN
    0.40
    鮪
    0.40
     qil
    0.40
    Activations Density 0.000%

    No Known Activations