© 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. 80325
    Prev
    Next
    INDEX
    Explanations

    English foundation mare

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

    open weights model

    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
    d
    0.52
    no
    0.47
    aría
    0.47
    nto
    0.46
    attr
    0.46
    ónimo
    0.44
    were
    0.43
    lá
    0.43
    =''
    0.43
     смысле
    0.42
    POSITIVE LOGITS
     muziek
    0.49
     suiv
    0.45
     narcotics
    0.45
     cujo
    0.45
     cuya
    0.44
     counterpart
    0.43
     daran
    0.43
     tx
    0.41
     accompagn
    0.41
     اتباع
    0.41
    Activations Density 0.006%

    No Known Activations