© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 7795
    Prev
    Next
    INDEX
    Explanations

    applications, problems, use cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_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
    and
    0.22
    ac
    0.21
    are
    0.20
    un
    0.20
    –
    0.20
    -,
    0.20
    im
    0.19
    ib
    0.19
    raw
    0.19
    o
    0.19
    POSITIVE LOGITS
     ఇది
    0.28
     ከአ
    0.26
    选项
    0.26
    ಾಗಿತ್ತು
    0.26
    体系
    0.25
    ያዎች
    0.25
    選項
    0.24
     cues
    0.23
     ਤੁ
    0.23
     নিদর্শন
    0.23
    Activations Density 0.289%

    No Known Activations