© 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. 53220
    Prev
    Next
    INDEX
    Explanations

    common words followed by various tokens

    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
    轴
    0.47
     produtos
    0.44
    it
    0.43
    ului
    0.43
     ajustes
    0.43
     bedrijf
    0.42
    ș
    0.42
    射
    0.42
     malzeme
    0.42
    হ
    0.42
    POSITIVE LOGITS
     تفسیر
    0.46
    identified
    0.46
     збере
    0.46
    LOOK
    0.45
    fashioned
    0.44
     போலவே
    0.43
    小さい
    0.43
     самой
    0.42
     Climb
    0.42
     disenfranch
    0.42
    Activations Density 0.004%

    No Known Activations