© 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. 1166
    Prev
    Next
    INDEX
    Explanations

    technical or foreign words

    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
     (‘
    1.46
     (=
    1.39
    hoea
    1.35
     (€
    1.30
     (£
    1.29
    コツ
    1.28
    真是
    1.27
    Ǧ
    1.26
     (.)
    1.26
    Encyclopedia
    1.26
    POSITIVE LOGITS
     combustible
    1.37
     энерго
    1.36
     autonomic
    1.34
     spawn
    1.33
    <unused1874>
    1.33
     ozone
    1.32
    spawn
    1.32
     silicate
    1.26
    男性
    1.26
    وجوان
    1.25
    Activations Density 0.728%

    No Known Activations