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. 11705
    Prev
    Next
    INDEX
    Explanations

    abstract concepts, often followed by 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_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
     είναι
    0.63
     bukanlah
    0.50
     transcends
    0.49
     is
    0.45
     está
    0.45
    은
    0.44
     është
    0.43
     değildir
    0.43
     differs
    0.43
    이
    0.41
    POSITIVE LOGITS
    );
    0.49
    ۔
    0.47
    。
    0.46
    :
    0.46
    ):
    0.45
    ',
    0.44
    .
    0.42
     a
    0.42
     כאשר
    0.42
    (),
    0.41
    Activations Density 0.157%

    No Known Activations