© 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. 13987
    Prev
    Next
    INDEX
    Explanations

    floors and years

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

    considers or considered

    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
     Analytics
    0.42
    ِه
    0.42
    dat
    0.41
     queries
    0.41
     همچ
    0.40
     analytics
    0.40
    :
    0.40
    ////////////////
    0.39
    lat
    0.39
    daki
    0.38
    POSITIVE LOGITS
     botched
    0.54
     négl
    0.52
    텍
    0.52
     ucc
    0.50
    uraea
    0.50
    괵
    0.49
     जोड़ा
    0.49
    orini
    0.49
     différence
    0.49
     Oahu
    0.49
    Activations Density 0.000%

    No Known Activations