© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 3246
    Prev
    Next
    INDEX
    Explanations

    it's not or it's important

    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_22_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
    s
    1.07
    ों
    0.98
    t
    0.93
    r
    0.91
    l
    0.91
    ים
    0.84
    y
    0.82
    and
    0.82
    or
    0.80
    т
    0.80
    POSITIVE LOGITS
     been
    1.98
     gotta
    1.36
     BEEN
    1.34
     gotten
    1.32
     impossible
    1.32
    been
    1.30
     got
    1.28
     raining
    1.28
     Been
    1.25
     worth
    1.25
    Activations Density 0.433%

    No Known Activations