© 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. 32966
    Prev
    Next
    INDEX
    Explanations

    let's estimate or say

    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
    쐞
    0.57
     través
    0.50
    ほとんど
    0.46
     mainly
    0.45
     comandos
    0.45
     almost
    0.44
     hauptsächlich
    0.44
     quase
    0.43
     kautta
    0.43
     pInBuffer
    0.42
    POSITIVE LOGITS
    Electron
    0.52
    Scale
    0.50
     απαι
    0.46
    璺
    0.46
    実際に
    0.45
    ཧ
    0.45
    ınıza
    0.44
     โ
    0.44
    💰
    0.44
    Annual
    0.44
    Activations Density 0.006%

    No Known Activations