© 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. 96719
    Prev
    Next
    INDEX
    Explanations

    manage your playlist

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

    sour cream

    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
     အမျိုး
    0.51
    ಗ
    0.48
    涎
    0.47
     област
    0.47
    秞
    0.46
     сала
    0.46
    sigmaf
    0.46
    вся
    0.45
     കേസ
    0.45
     перспек
    0.45
    POSITIVE LOGITS
     world
    0.52
     세계
    0.47
     antelope
    0.46
    ↵
    0.46
     spac
    0.44
     BLACK
    0.44
     space
    0.42
     accurately
    0.42
     Black
    0.41
     configuration
    0.41
    Activations Density 0.001%

    No Known Activations