© 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. 192049
    Prev
    Next
    INDEX
    Explanations

    prices, download, tickets, liberal

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

    actions and functions

    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
    ári
    0.47
     அழக
    0.46
    兔子
    0.45
    呲
    0.45
    趾
    0.44
    gelt
    0.44
     prilikom
    0.44
     במהלך
    0.43
    故意
    0.42
    ען
    0.42
    POSITIVE LOGITS
    _{
    0.46
    𝕞
    0.44
     Remove
    0.43
    ड़ब
    0.43
     Retrieve
    0.42
     Tuesday
    0.42
     Sélectionnez
    0.41
     Activate
    0.41
     Download
    0.41
    เลือก
    0.40
    Activations Density 0.001%

    No Known Activations