© 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
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1570
    Prev
    Next
    INDEX
    Explanations

    NV center, group, scene, Hope

    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
    (
    1.57
    -
    1.37
    いは
    1.33
     leaks
    1.29
    是最
    1.29
    コツ
    1.29
    ients
    1.29
     proceeds
    1.27
    様子
    1.25
    簿
    1.24
    POSITIVE LOGITS
    7
    3.71
    8
    3.49
    type
    3.48
    6
    3.39
    5
    3.35
    ак
    3.27
     стоя
    3.24
    ٧
    3.20
    rinsic
    3.19
    wake
    3.16
    Activations Density 0.524%

    No Known Activations