© 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. 198165
    Prev
    Next
    INDEX
    Explanations

    our customer service

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

    but AI

    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
     acciaio
    0.52
     fhall
    0.47
    ₁+
    0.46
     }^{
    0.46
    ∮
    0.46
     தெளி
    0.45
     anyag
    0.45
     textil
    0.45
    볍
    0.45
    
    0.45
    POSITIVE LOGITS
     Love
    0.54
     Honor
    0.46
     Rich
    0.46
     offense
    0.46
     วิ
    0.45
     Mother
    0.45
     കാ
    0.44
     Better
    0.44
     కో
    0.43
    Codes
    0.43
    Activations Density 0.000%

    No Known Activations