© 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-3-270M-IT
    3. 12-GEMMASCOPE-2-RES-65K
    4. 1073
    Prev
    Next
    INDEX
    Explanations

    topmost nodes, human-like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
    ,
    4.25
    、
    3.16
    ،
    2.89
    ,
    2.64
    (
    2.63
    ,|
    2.60
    :
    2.47
    .
    2.46
    ,<
    2.44
    |
    2.38
    POSITIVE LOGITS
     perceiving
    3.10
    Diffuse
    2.68
     especialmente
    2.66
     classifying
    2.65
    7
    2.63
     idling
    2.62
    rinsic
    2.62
     permitt
    2.61
     accruing
    2.56
     creando
    2.54
    Activations Density 1.653%

    No Known Activations