© 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. 145636
    Prev
    Next
    INDEX
    Explanations

    recipee, been regularly, with the, make ideas, to remember, such copying, HANDLE END, earth and

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

    formulas, lists, and cultural knowledge

    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
     ništa
    0.55
    லாமல்
    0.54
    ധികം
    0.53
     નંબર
    0.52
    惶
    0.52
    asitriangular
    0.50
     difíciles
    0.48
    ibilidades
    0.48
     questões
    0.46
    CTOGRAM
    0.46
    POSITIVE LOGITS
    ↵
    0.51
    5
    0.50
    0.48
    3
    0.47
    7
    0.47
    4
    0.46
     d
    0.43
    </em>
    0.43
    2
    0.42
    \
    0.42
    Activations Density 0.001%

    No Known Activations