© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 123417
    Prev
    Next
    INDEX
    Explanations

    technical terms and descriptions

    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
     Cela
    0.54
     la
    0.52
     Elena
    0.51
     Em
    0.49
     né
    0.49
     to
    0.49
     X
    0.49
     accusations
    0.49
     Majka
    0.48
     Pedro
    0.48
    POSITIVE LOGITS
     phenolic
    0.47
    াল
    0.46
    плат
    0.45
    Simulator
    0.45
    ал
    0.44
    HCl
    0.43
    орга
    0.42
    াহ
    0.42
    зуа
    0.41
    );\
    0.41
    Activations Density 0.004%

    No Known Activations