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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 31903
    Prev
    Next
    INDEX
    Explanations

    C++ includes

    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_16_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
    ные
    0.84
    ，
    0.82
    и
    0.80
    مان
    0.77
     ihren
    0.77
    ،
    0.76
    ية
    0.75
    ро
    0.74
    ：
    0.74
    ة
    0.74
    POSITIVE LOGITS
    abhavena
    0.80
    punyai
    0.73
    𝚏
    0.72
    at
    0.69
    iš
    0.69
    gripper
    0.69
     indah
    0.68
     сча
    0.68
    ių
    0.67
     escog
    0.67
    Activations Density 0.009%

    No Known Activations