© 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. 109262
    Prev
    Next
    INDEX
    Explanations

    things to consider

    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
    '
    1.21
    ’
    0.80
    n
    0.67
    ,'
    0.66
    x
    0.65
     сопровожда
    0.59
    น
    0.59
    '')
    0.59
     powied
    0.58
     некоторое
    0.58
    POSITIVE LOGITS
     at
    0.71
    geht
    0.64
     Einfluss
    0.63
    8
    0.63
    6
    0.61
    AR
    0.60
    9
    0.60
     a
    0.58
    م
    0.58
    3
    0.57
    Activations Density 0.010%

    No Known Activations