© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3582
    Prev
    Next
    INDEX
    Explanations

    fight and combat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_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
    pq
    1.28
     OpenAPI
    1.18
     Bloomfield
    1.17
    OBS
    1.14
     Greenwood
    1.13
     Lav
    1.12
     SRS
    1.10
    ଓ
    1.09
     uncond
    1.08
     alterações
    1.08
    POSITIVE LOGITS
     fights
    2.78
    fighting
    2.74
    fight
    2.72
     fight
    2.68
     battles
    2.64
    battle
    2.62
     battle
    2.59
     fighting
    2.58
    fought
    2.55
     fought
    2.52
    Activations Density 0.151%

    No Known Activations