© 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. 103897
    Prev
    Next
    INDEX
    Explanations

    the rest will

    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
    ні
    0.66
     hẳn
    0.65
     doorbell
    0.64
     liar
    0.63
    ાડ
    0.63
    、
    0.63
    <0x91>
    0.62
    ્ષ
    0.62
     mortgage
    0.61
    ực
    0.61
    POSITIVE LOGITS
    c
    0.78
    Utils
    0.76
    6
    0.76
    x
    0.75
    9
    0.75
    8
    0.75
    é
    0.74
    其他
    0.72
    4
    0.72
    have
    0.70
    Activations Density 0.002%

    No Known Activations