© 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. 15167
    Prev
    Next
    INDEX
    Explanations

    origins of core concepts

    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
     Marques
    0.51
     transluc
    0.50
     inlay
    0.48
     nibb
    0.46
    ♢
    0.46
    ripciones
    0.45
     मसाले
    0.45
    ”。
    0.45
    )”.
    0.44
    窥
    0.44
    POSITIVE LOGITS
    ст
    0.45
    US
    0.45
    ५
    0.45
     আমেরিকার
    0.44
    ос
    0.43
     partly
    0.42
     cours
    0.42
    во
    0.41
    чи
    0.41
    ή
    0.41
    Activations Density 0.002%

    No Known Activations