© 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. 24829
    Prev
    Next
    INDEX
    Explanations

    invade, invasion, invasive

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

    invasion and penetration

    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
    icester
    0.47
     Witnesses
    0.46
    ارہ
    0.45
    DoesNotExist
    0.45
     Hobson
    0.45
     मिरर
    0.44
    ringstream
    0.44
    ≜
    0.44
    mirror
    0.43
     Concentrate
    0.43
    POSITIVE LOGITS
     invade
    1.42
     invasion
    1.39
     invaded
    1.37
     invas
    1.23
     invasions
    1.21
     invading
    1.19
    入侵
    1.16
     проник
    1.14
    侵
    1.14
     penet
    1.12
    Activations Density 0.070%

    No Known Activations