© 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. 466
    Prev
    Next
    INDEX
    Explanations

    starting or beginning

    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
    chequer
    1.23
    ’
    1.20
     Amongst
    1.15
    One
    1.13
    '
    1.13
     lược
    1.13
    をご覧ください
    1.11
    佢
    1.10
    isesti
    1.10
     historians
    1.08
    POSITIVE LOGITS
     iniciar
    2.02
     iniziare
    2.00
    زاده
    1.92
     încep
    1.91
     시작
    1.89
     empezar
    1.89
     comenzar
    1.89
    abhut
    1.88
     nasc
    1.85
     началом
    1.84
    Activations Density 0.220%

    No Known Activations