© 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. 110253
    Prev
    Next
    INDEX
    Explanations

    have need needs got

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

    universal religion

    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
    fp
    0.49
    פ
    0.48
    '];
    0.47
     supon
    0.46
    ק
    0.45
     冖
    0.45
     sup
    0.45
    rá
    0.44
    ส
    0.43
    唃
    0.43
    POSITIVE LOGITS
    Charset
    0.49
    FormData
    0.46
    ledi
    0.45
    iled
    0.44
    窍
    0.43
    Chemical
    0.43
    anlage
    0.42
    쥐
    0.42
    тном
    0.41
    স্তর
    0.41
    Activations Density 0.001%

    No Known Activations