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-262K
    4. 43939
    Prev
    Next
    INDEX
    Explanations

    converting text to lowercase

    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
    ਿਰ
    0.45
    英語
    0.43
    プリング
    0.42
     crowned
    0.42
    トゥ
    0.42
    _{+}$
    0.41
    princess
    0.41
    ২০
    0.41
    名词
    0.41
    फ्टर
    0.41
    POSITIVE LOGITS
    o
    0.52
     Bunker
    0.47
     scorecard
    0.47
    rometer
    0.46
     missione
    0.44
     search
    0.44
     Grange
    0.44
     Passage
    0.43
     RANGE
    0.43
     missile
    0.42
    Activations Density 0.002%

    No Known Activations