© 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. 244245
    Prev
    Next
    INDEX
    Explanations

    theory and limits

    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
    ','#
    0.47
    прав
    0.46
    らしい
    0.44
     \#
    0.44
    ка
    0.43
    PHIL
    0.43
    bumps
    0.43
    کار
    0.42
     possibly
    0.42
     and
    0.42
    POSITIVE LOGITS
     profunda
    0.51
     Erinner
    0.48
     establecidos
    0.48
     限
    0.48
     théorie
    0.47
     límites
    0.47
     मस
    0.46
     establecidas
    0.46
     Teor
    0.46
     teórico
    0.46
    Activations Density 0.001%

    No Known Activations