© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 2487
    Prev
    Next
    INDEX
    Explanations

    error reporting

    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
     in
    1.18
     by
    1.18
     at
    1.17
     with
    1.16
     of
    1.15
     when
    1.13
     g
    1.13
     n
    1.13
     if
    1.11
     may
    1.11
    POSITIVE LOGITS
    Про
    1.69
    Ко
    1.65
    Warning
    1.64
    За
    1.64
    По
    1.63
    На
    1.61
    Here
    1.60
    Мо
    1.59
    У
    1.59
    Ма
    1.57
    Activations Density 0.058%

    No Known Activations