© 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. 83895
    Prev
    Next
    INDEX
    Explanations

    ingredients and disclaimers

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

    activities and prioritization

    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
    \}$
    0.59
    ي
    0.57
    ه
    0.55
    M
    0.53
    ע
    0.53
    D
    0.52
    Raj
    0.51
    '=>
    0.51
    하지
    0.51
    י
    0.51
    POSITIVE LOGITS
     diving
    0.53
     traced
    0.51
     leaping
    0.49
     ១
    0.47
     сфе
    0.46
     delving
    0.45
     Examine
    0.45
     sprinting
    0.44
     tracing
    0.44
     recklessly
    0.44
    Activations Density 0.000%

    No Known Activations