© 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. 123236
    Prev
    Next
    INDEX
    Explanations

    save, life, death, expense, solution

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

    measures duration and time scales

    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
    (|
    0.44
     ►
    0.43
    >/
    0.42
    📱
    0.42
    >%
    0.42
    🛴
    0.41
     มา
    0.41
     enrolment
    0.41
    iert
    0.41
    >;
    0.41
    POSITIVE LOGITS
     significativas
    0.49
    可能性
    0.45
     රස
    0.44
     perfección
    0.43
    orde
    0.43
    elesaian
    0.42
    的可能性
    0.42
    在他的
    0.40
    ட்டார்
    0.40
    နိုင်
    0.40
    Activations Density 0.006%

    No Known Activations