© 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. 115383
    Prev
    Next
    INDEX
    Explanations

    embryo adoption

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

    alter/change/influence trajectory/outlook

    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
     Martian
    0.53
     Cabrera
    0.51
     Soc
    0.50
     Uranium
    0.49
     Correa
    0.49
     Louisiana
    0.49
     Leid
    0.49
    ي
    0.47
     Mafia
    0.46
     Ocean
    0.46
    POSITIVE LOGITS
    domain
    0.52
    spring
    0.49
    fato
    0.49
    asmine
    0.48
    date
    0.47
    scopic
    0.47
    claration
    0.46
    oulder
    0.46
    ellem
    0.46
    嫵
    0.46
    Activations Density 0.000%

    No Known Activations