© 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. 3183
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and formulas

    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
     auditory
    0.91
    =',')
    0.85
    ografie
    0.83
     charismatic
    0.81
    }=\{
    0.80
     salaried
    0.80
     nicknamed
    0.80
     Tuesdays
    0.80
     poeta
    0.78
     entrenched
    0.78
    POSITIVE LOGITS
     ((
    1.82
    ((
    1.81
     [(
    1.75
    [(
    1.69
     (((
    1.51
    frac
    1.46
    (((
    1.44
    ([(
    1.40
    ((-
    1.22
     √(
    1.22
    Activations Density 0.575%

    No Known Activations