© 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. 25887
    Prev
    Next
    INDEX
    Explanations

    fighting and struggling

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

    fighting for or against something

    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
    ü
    0.69
    ą
    0.63
    ه‌
    0.61
     Voyages
    0.61
    मोट
    0.59
    مان
    0.59
    সহ
    0.59
    ɻ
    0.59
    حية
    0.58
    সংযোগ
    0.58
    POSITIVE LOGITS
     battles
    1.13
     fight
    1.10
     fought
    1.05
     fights
    0.95
     battle
    0.93
    Fight
    0.92
     Fight
    0.91
     batalha
    0.90
    fight
    0.89
     kämp
    0.89
    Activations Density 0.104%

    No Known Activations