© 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. 18736
    Prev
    Next
    INDEX
    Explanations

    form below and click "Submit"

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

    res.send

    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
    旯
    0.41
    ይን
    0.40
    AfterTax
    0.39
     ఎక్కువ
    0.38
     এটির
    0.38
    产生了
    0.36
    后者
    0.36
    kepsilon
    0.36
    MinIntensity
    0.36
    猞
    0.36
    POSITIVE LOGITS
    el
    0.40
    rum
    0.38
     principais
    0.37
     know
    0.37
     understand
    0.36
     fundament
    0.36
    riving
    0.36
     entender
    0.36
    first
    0.35
     believed
    0.34
    Activations Density 0.028%

    No Known Activations