© 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. 107759
    Prev
    Next
    INDEX
    Explanations

    until pain

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

    describing context or relation

    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
    aud
    0.49
     という
    0.44
     入り
    0.43
    CLUSIVE
    0.42
                         
    0.42
    ALT
    0.40
     啊
    0.40
     fastest
    0.40
     RUN
    0.40
    htmlspecialchars
    0.40
    POSITIVE LOGITS
    граф
    0.55
    ចាយ
    0.49
    igheten
    0.48
    ჭ
    0.48
    toj
    0.47
    mato
    0.47
    iejęt
    0.46
    jmath
    0.46
    stice
    0.46
     ਦਿੱ
    0.46
    Activations Density 0.000%

    No Known Activations