© 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-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 11094
    Prev
    Next
    INDEX
    Explanations

    programming function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    pé
    0.46
    something
    0.44
    ḥ
    0.41
    <unused2014>
    0.41
    rono
    0.41
    angulo
    0.41
    res
    0.41
    such
    0.40
    した
    0.40
    nothing
    0.40
    POSITIVE LOGITS
     getDefault
    0.44
     getConnection
    0.41
     buildTypes
    0.41
    !?
    0.40
    ?”
    0.40
    ?!
    0.37
    ؟!
    0.37
     Scandinavian
    0.36
    ?
    0.36
     buildFor
    0.36
    Activations Density 0.025%

    No Known Activations