Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 211046
    Prev
    Next
    INDEX
    Explanations

    saturation percent, fairly straightforward

    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
    arko
    0.39
    艷
    0.37
    tipo
    0.37
    razi
    0.37
     Economies
    0.36
     debat
    0.36
    ACI
    0.36
     Producto
    0.36
    RIC
    0.35
     rmg
    0.35
    POSITIVE LOGITS
    aling
    0.39
    Bride
    0.38
     पाठ
    0.37
    पार
    0.37
    oclip
    0.37
     extant
    0.37
    థ
    0.37
    து
    0.36
     compl
    0.36
    тена
    0.36
    Activations Density 0.001%

    No Known Activations