© 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. 9-GEMMASCOPE-2-RES-262K
    7. 11587
    Prev
    Next
    INDEX
    Explanations

    vowel sounds and single letters

    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_9_width_262k_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
    z
    1.80
    l
    1.75
    a
    1.73
    ر
    1.73
    at
    1.71
    is
    1.71
    r
    1.69
    w
    1.61
    i
    1.59
    ل
    1.57
    POSITIVE LOGITS
    theless
    1.15
    າດ
    0.96
     totaling
    0.96
    mselves
    0.94
    रिडोर
    0.93
     önem
    0.90
     Honorary
    0.90
     radiated
    0.90
    Cuánt
    0.87
    ly
    0.86
    Activations Density 0.080%

    No Known Activations