© 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-65K
    7. 4862
    Prev
    Next
    INDEX
    Explanations

    types of Be

    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_65k_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
     R
    0.44
     Publikum
    0.43
     originated
    0.43
    *}
    0.42
    原
    0.42
     I
    0.42
    –
    0.41
     Denis
    0.41
    ме
    0.41
     Sandler
    0.41
    POSITIVE LOGITS
     Ү
    0.52
    striatis
    0.51
     интегра
    0.48
    funciones
    0.48
    pInBuffer
    0.47
     elevating
    0.46
     אל
    0.46
    nBitCount
    0.46
    耱
    0.45
     ውስ
    0.45
    Activations Density 0.000%

    No Known Activations