© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 56974
    Prev
    Next
    INDEX
    Explanations

    code syntax, including parentheses and keywords

    np_acts-logits-general · gemini-2.5-flash-lite

    programming constructs and data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (".")
    0.46
    ('/')
    0.43
    ("/")
    0.41
    łem
    0.40
    (".");
    0.39
    umuza
    0.39
    ('.')
    0.38
     determinato
    0.38
     {}".
    0.38
    ruci
    0.38
    POSITIVE LOGITS
    ("",
    0.85
    ('',
    0.76
    ({},
    0.74
     "",
    0.73
    ([],
    0.70
     _,
    0.68
     '',
    0.63
    _,
    0.63
    (_,
    0.62
    {},
    0.61
    Activations Density 0.005%

    No Known Activations