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. 35248
    Prev
    Next
    INDEX
    Explanations

    those ... in, his alliance

    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
    婫
    0.46
    ánico
    0.46
    ากาศ
    0.45
    𝙠
    0.44
     सपना
    0.43
    კი
    0.43
    ainted
    0.42
     sueños
    0.42
     społecz
    0.42
     כל
    0.41
    POSITIVE LOGITS
     T
    0.43
     VIII
    0.43
     quadrant
    0.42
     tuff
    0.42
     wheelbase
    0.42
     Short
    0.41
     VII
    0.40
     Pathway
    0.40
     polo
    0.39
     $\
    0.39
    Activations Density 0.001%

    No Known Activations