© 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. 136636
    Prev
    Next
    INDEX
    Explanations

    critical step

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

    While their

    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
    S
    0.52
    м
    0.52
    ре
    0.51
    近
    0.51
    P
    0.49
    ри
    0.49
    р
    0.49
     incr
    0.49
    特
    0.47
     Mar
    0.47
    POSITIVE LOGITS
     けど
    0.52
    。</
    0.48
     書い
    0.48
     及び
    0.46
    imą
    0.45
    <0x1D>
    0.45
     ہے۔
    0.44
     établissements
    0.44
     ।”
    0.44
    onać
    0.43
    Activations Density 0.000%

    No Known Activations