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. 14402
    Prev
    Next
    INDEX
    Explanations

    adding or granting access

    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
     Bagaimana
    0.41
     insanlar
    0.37
    KindOf
    0.36
     बतौर
    0.35
    ưởng
    0.35
     இருக்கும்
    0.35
    看看
    0.35
    ﷽
    0.35
     कॉम्प
    0.35
     буде
    0.34
    POSITIVE LOGITS
     modifying
    0.42
     elects
    0.41
    𒄿
    0.41
     equivari
    0.40
     championships
    0.40
     postérieure
    0.40
     coats
    0.40
     rayas
    0.39
     backwards
    0.39
    ດີ
    0.39
    Activations Density 0.000%

    No Known Activations