© 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. 155876
    Prev
    Next
    INDEX
    Explanations

    ratings, scores, fish, licensed, offering

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

    understanding perception and language

    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
     preserves
    0.48
     scans
    0.46
     logs
    0.46
    Ꮦ
    0.46
     বয়স
    0.45
     의한
    0.45
    >$
    0.45
    $.\
    0.44
     labels
    0.44
     TELE
    0.44
    POSITIVE LOGITS
    سه
    0.52
    iched
    0.50
    usalem
    0.48
    igual
    0.47
    هش
    0.43
    orgung
    0.42
     autumnal
    0.41
     succinct
    0.41
     اضافه
    0.41
    imensional
    0.40
    Activations Density 0.000%

    No Known Activations