© 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. 120590
    Prev
    Next
    INDEX
    Explanations

    parity, spindle, inversion

    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
    ექს
    0.53
    ัญญา
    0.50
    .}}
    0.50
    ॉकलेट
    0.49
    いずれ
    0.49
    멩
    0.49
    タク
    0.49
     anguish
    0.48
     Haifa
    0.48
    ぐ
    0.48
    POSITIVE LOGITS
     أن
    0.61
     repar
    0.61
     of
    0.57
     secretário
    0.55
    IW
    0.54
     за
    0.53
     پ
    0.53
     в
    0.52
    ça
    0.52
     lanç
    0.52
    Activations Density 0.000%

    No Known Activations