Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12642
    Prev
    Next
    INDEX
    Explanations

    sleeping and resting

    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_16k_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
    iscal
    0.48
    us
    0.47
     By
    0.46
    math
    0.46
     .
    0.44
     >>
    0.44
    our
    0.42
    an
    0.42
    isp
    0.41
    profile
    0.41
    POSITIVE LOGITS
     atomizer
    0.53
    ätten
    0.49
     piezoelectric
    0.45
    电压
    0.45
     PROM
    0.45
     stoneware
    0.45
     περί
    0.44
    PROM
    0.43
    蘸
    0.43
    𝑃
    0.42
    Activations Density 0.009%

    No Known Activations