© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 2255
    Prev
    Next
    INDEX
    Explanations

    hash symbol or comment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ･･
    0.82
     ì
    0.68
     ـ
    0.66
    ꧂
    0.65
    ∙
    0.65
    ufieurs
    0.65
    ጢ
    0.64
    \_
    0.64
     createContext
    0.64
    ———
    0.63
    POSITIVE LOGITS
     #
    6.05
    #
    5.79
     (#
    4.14
    .#
    4.05
     \#
    3.96
    #,
    3.91
    ＃
    3.84
    ,#
    3.83
     $\#
    3.64
     #(
    3.63
    Activations Density 0.849%

    No Known Activations