© 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
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 6905
    Prev
    Next
    INDEX
    Explanations

    explaining processes or stages

    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
    '
    0.94
    ,
    0.94
    ur
    0.93
    :
    0.91
    .
    0.87
    it
    0.86
    -
    0.86
    we
    0.84
    and
    0.83
    he
    0.82
    POSITIVE LOGITS
     Revisited
    1.27
     Optional
    1.13
     Số
    1.10
     Các
    1.10
     Tiếp
    1.09
     Showing
    1.09
     Mythology
    1.09
     Expansion
    1.08
     Lifecycle
    1.08
     Exploring
    1.08
    Activations Density 1.795%

    No Known Activations