© 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. 6861
    Prev
    Next
    INDEX
    Explanations

    come, behind, mother, eat

    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
    c
    0.55
    j
    0.52
     конкре
    0.48
     Cement
    0.47
    ри
    0.47
     Occidental
    0.44
    具体的
    0.44
     Sigma
    0.43
    جهات
    0.43
     Support
    0.42
    POSITIVE LOGITS
     aturan
    0.59
    etail
    0.55
    ේව
    0.55
    putted
    0.50
    ,_-
    0.49
     හෝ
    0.49
     skirts
    0.49
    ونم
    0.49
     syllabus
    0.48
    NGTH
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.