© 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. 31-GEMMASCOPE-2-RES-262K
    7. 71207
    Prev
    Next
    INDEX
    Explanations

    job or web3

    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_31_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
    FileNotFound
    0.46
    ты
    0.45
    最为
    0.44
    usu
    0.42
    itm
    0.42
    embangan
    0.42
    attam
    0.41
    0
    0.41
    clang
    0.41
    пол
    0.40
    POSITIVE LOGITS
     evidentiary
    0.47
     Dee
    0.46
     tenuous
    0.46
     Mā
    0.45
     tiden
    0.45
     certeza
    0.44
     Św
    0.44
     compro
    0.43
     eingerichtet
    0.43
    AssetDiscovery
    0.43
    Activations Density 0.003%

    No Known Activations