© 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. 155937
    Prev
    Next
    INDEX
    Explanations

    quantifying time and action

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

    "a number" or "phone number"

    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
    >{
    0.52
     Burma
    0.49
     ఉంది
    0.48
    }{\
    0.48
     filial
    0.46
     sickly
    0.46
     postwar
    0.45
     etapa
    0.45
     fecund
    0.45
     profunda
    0.44
    POSITIVE LOGITS
    that
    0.62
    报告
    0.50
    亭
    0.49
    反応
    0.48
    高速
    0.47
    this
    0.46
    那种
    0.45
    requests
    0.45
    协议
    0.45
    reactions
    0.44
    Activations Density 0.001%

    No Known Activations