© 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. 227485
    Prev
    Next
    INDEX
    Explanations

    elapsed time since epoch

    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
    elling
    0.64
    ém
    0.53
    ción
    0.53
    emies
    0.52
    ๖
    0.51
    ème
    0.50
    öl
    0.50
    overrightarrow
    0.50
    ation
    0.49
    ем
    0.49
    POSITIVE LOGITS
     nantinya
    0.49
     diap
    0.48
    g
    0.48
    >>)
    0.46
    ’)
    0.45
    と思っています
    0.44
    却没有
    0.44
    ────────
    0.43
     chmod
    0.43
    套
    0.42
    Activations Density 0.001%

    No Known Activations