© 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. 139029
    Prev
    Next
    INDEX
    Explanations

    text with structural elements

    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
    nętr
    0.49
    gulpfile
    0.46
    Lus
    0.46
    ร์
    0.46
    κος
    0.45
    ላይ
    0.44
    ੫
    0.44
     microorgan
    0.43
    onOptions
    0.43
    靱
    0.42
    POSITIVE LOGITS
     podría
    0.42
     ব
    0.42
     steg
    0.41
     jadi
    0.41
     ఎదు
    0.40
     అధ
    0.39
     det
    0.39
    您可以
    0.39
     поч
    0.39
    我就
    0.39
    Activations Density 0.001%

    No Known Activations