© 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. 2990
    Prev
    Next
    INDEX
    Explanations

    product attributes and value

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

    explain with context

    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
    к
    0.39
     गि
    0.38
    ེ
    0.38
     கல்லற
    0.38
     கல்லறை
    0.38
     인간
    0.37
    ฟา
    0.37
     பக்க
    0.37
    others
    0.36
    ritual
    0.36
    POSITIVE LOGITS
     (
    0.49
     of
    0.40
    -
    0.38
     [
    0.38
    /
    0.37
     যেহেতু
    0.36
     PCR
    0.35
    :
    0.35
     attempted
    0.35
     confirmed
    0.33
    Activations Density 0.168%

    No Known Activations