© 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. 7431
    Prev
    Next
    INDEX
    Explanations

    location and context specifiers

    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
    arschijnlijk
    0.68
    োই
    0.66
    ത്തര
    0.65
    തായ
    0.64
    ipay
    0.63
    갚
    0.63
     አለበት
    0.62
    क़्त
    0.62
    бе
    0.60
    讫
    0.60
    POSITIVE LOGITS
     where
    5.83
    where
    5.00
     donde
    4.58
     Where
    4.54
    Where
    4.46
     wherein
    4.41
     où
    4.34
     где
    4.22
     hvor
    4.10
     WHERE
    4.06
    Activations Density 0.574%

    No Known Activations