© 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. 188643
    Prev
    Next
    INDEX
    Explanations

    measure rotational torque using

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

    record, interactions, package, spacing

    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
     حكوم
    0.49
    سب
    0.44
     لمع
    0.44
    币
    0.43
     возник
    0.43
    Cer
    0.42
    ocos
    0.42
    령
    0.42
     정부
    0.42
     خانو
    0.41
    POSITIVE LOGITS
    "</
    0.47
     marshmallows
    0.46
     serene
    0.45
     Einstellung
    0.45
     αλλά
    0.44
     Odisha
    0.44
    ANIUM
    0.44
     apex
    0.42
    হইতে
    0.42
     Pinn
    0.42
    Activations Density 0.000%

    No Known Activations