Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 581
    Prev
    Next
    INDEX
    Explanations

    array and list operations

    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_65k_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
     petites
    0.48
    auch
    0.47
     doctrines
    0.47
     sagte
    0.46
    อนไลน์
    0.46
    ongiorno
    0.45
    }=-
    0.45
    Magg
    0.45
     auch
    0.45
    Ruling
    0.44
    POSITIVE LOGITS
    [(
    0.58
     sorted
    0.57
     map
    0.56
     numpy
    0.54
     contains
    0.52
    ظم
    0.52
    isEmpty
    0.51
    র্ষ
    0.50
     indexOf
    0.50
     containing
    0.49
    Activations Density 0.336%

    No Known Activations