© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72771
    Prev
    Next
    INDEX
    Explanations

    force or physics concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     \"
    -2.80
    \
    -2.22
     muros
    -2.20
    .\"
    -2.19
     ``
    -2.17
     
    -2.17
    as
    -2.11
    廕
    -2.09
     Other
    -2.09
    䊉
    -2.06
    POSITIVE LOGITS
    镚
    2.56
    </sub>
    2.48
     leur
    2.36
    ſu
    2.25
     et
    2.25
    Ꮉ
    2.20
    力
    2.13
    >
    2.11
    providedIn
    2.09
    };
    2.02
    Activations Density 0.019%

    No Known Activations