© 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. 6468
    Prev
    Next
    INDEX
    Explanations

    defend against or protect from

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

    building networks and communication strategies

    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
     evolve
    0.47
     ellipse
    0.47
     obserw
    0.46
     cliff
    0.46
    }^{+}+
    0.46
     roundtable
    0.45
     dislocations
    0.45
     dioxide
    0.44
     圆
    0.44
    quiao
    0.44
    POSITIVE LOGITS
     угро
    0.46
     защита
    0.45
    সুল
    0.45
    ivos
    0.45
     защи
    0.45
     которой
    0.44
     защиту
    0.43
     seguro
    0.43
     Merchandise
    0.43
    FILE
    0.42
    Activations Density 0.000%

    No Known Activations