© 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. 61326
    Prev
    Next
    INDEX
    Explanations

    validation

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

    numbers, counts, or amounts

    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
    ૂ
    0.34
    ста
    0.33
    Ã
    0.33
    ू
    0.32
    ар
    0.32
    ин
    0.32
    স
    0.32
    as
    0.31
    ка
    0.30
    બ
    0.30
    POSITIVE LOGITS
     ///
    0.30
     seguente
    0.29
     gegeben
    0.28
     tyrant
    0.28
     tumour
    0.26
     laure
    0.26
     oth
    0.26
     tup
    0.26
     beggar
    0.26
     quercetin
    0.26
    Activations Density 0.130%

    No Known Activations