© 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. 86108
    Prev
    Next
    INDEX
    Explanations

    ward + en

    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
     ע
    0.70
     אי
    0.63
     maliciously
    0.61
     μυ
    0.61
     ק
    0.58
     אור
    0.57
     ב
    0.56
     ಬ
    0.56
     კონ
    0.56
     ন
    0.55
    POSITIVE LOGITS
    d
    0.55
    ps
    0.54
    dsp
    0.53
    up
    0.52
    v
    0.50
    dna
    0.49
    h
    0.48
    del
    0.47
    hr
    0.47
    end
    0.47
    Activations Density 0.000%

    No Known Activations