© 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. 26780
    Prev
    Next
    INDEX
    Explanations

    short stories or headboards

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

    fine tuning

    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
     igneous
    0.35
     europäischen
    0.34
     itinerant
    0.31
     evrops
    0.31
    ;.
    0.31
    ）、
    0.29
     erotic
    0.29
    )....
    0.29
     hypothalam
    0.29
     bhikkhu
    0.29
    POSITIVE LOGITS
    ers
    0.35
     따라서
    0.33
    э
    0.33
    b
    0.32
    -
    0.32
    bl
    0.30
    ck
    0.30
    -\\
    0.29
    ing
    0.29
    jähr
    0.29
    Activations Density 0.082%

    No Known Activations