© 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. 64879
    Prev
    Next
    INDEX
    Explanations

    found out

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

    found or came across

    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
    ombre
    0.49
    انہوں
    0.49
     Антон
    0.48
    قتل
    0.47
    enfants
    0.45
    bathroom
    0.45
     Екатерина
    0.45
    阕
    0.44
     subi
    0.44
     অস্বীক
    0.44
    POSITIVE LOGITS
     via
    0.58
     www
    0.48
     gem
    0.47
     PEP
    0.47
     discovered
    0.45
     cực
    0.43
    via
    0.42
     Via
    0.42
     கிடை
    0.42
     чрез
    0.42
    Activations Density 0.031%

    No Known Activations