© 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. 21925
    Prev
    Next
    INDEX
    Explanations

    numeric values, percentages, dates

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

    numbers and calculations

    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
     этим
    0.46
    getBlueTeam
    0.46
    锶
    0.46
     служ
    0.43
    auern
    0.43
     కావ
    0.43
    जीलैंड
    0.41
     욕
    0.41
    两种
    0.41
     తాగ
    0.41
    POSITIVE LOGITS
     dupa
    0.41
     methodical
    0.40
     incredibly
    0.38
     citas
    0.38
     penchant
    0.38
     armored
    0.37
     frequency
    0.37
     proven
    0.37
     resonance
    0.37
     propiedades
    0.37
    Activations Density 0.000%

    No Known Activations