© 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. 1103
    Prev
    Next
    INDEX
    Explanations

    sequence prediction

    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
    ’
    2.60
    '
    2.52
    сро
    2.42
    ld
    2.32
    dated
    2.28
    (
    2.26
     her
    2.25
     يل
    2.21
     بف
    2.18
    lor
    2.16
    POSITIVE LOGITS
     makeSound
    2.65
    rinsic
    2.61
    <unused1874>
    2.43
     totalSupply
    2.34
    iawan
    2.33
     Spawn
    2.32
    adayo
    2.30
    Diffuse
    2.28
    argaan
    2.21
    ísk
    2.20
    Activations Density 0.490%

    No Known Activations