© 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. 33015
    Prev
    Next
    INDEX
    Explanations

    ending punctuation

    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
     database
    0.40
     👉
    0.39
     facades
    0.39
     $\{\
    0.38
    yscraper
    0.38
    ceral
    0.38
     xī
    0.38
     DISCOUNT
    0.37
    )$\\
    0.37
     BadRequest
    0.37
    POSITIVE LOGITS
    appreci
    0.48
    engineering
    0.43
     инженер
    0.43
    isomer
    0.42
    vigor
    0.42
    printing
    0.41
    Laboratory
    0.41
    ج
    0.41
     appreciable
    0.41
    temperature
    0.41
    Activations Density 0.002%

    No Known Activations