© 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. 1049
    Prev
    Next
    INDEX
    Explanations

    quoted text ends

    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
    ～。
    1.23
    planned
    1.19
     ge
    1.17
     pa
    1.16
     pip
    1.14
    pan
    1.13
    。【
    1.12
     organisation
    1.11
    سى
    1.11
    ަ
    1.11
    POSITIVE LOGITS
    」
    1.43
    »
    1.20
    ”
    1.19
    "
    1.16
    7
    1.16
    8
    1.15
    4
    1.14
    °
    1.13
    6
    1.13
    °)
    1.11
    Activations Density 2.726%

    No Known Activations