© 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. 40-GEMMASCOPE-2-RES-262K
    7. 191377
    Prev
    Next
    INDEX
    Explanations

    word characters (letters, numbers, underscores)

    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_40_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
     parsing
    0.41
     "|"
    0.38
     discouraging
    0.37
     countDown
    0.37
    ຽ
    0.37
     Jonathan
    0.36
     "|
    0.36
    涜
    0.36
     سره
    0.36
    omegranate
    0.36
    POSITIVE LOGITS
     Indo
    0.39
    PDF
    0.35
    pdf
    0.34
    Дата
    0.34
    Mu
    0.33
     பொ
    0.33
     tạo
    0.33
     ചേ
    0.33
     voici
    0.33
    nutí
    0.33
    Activations Density 0.001%

    No Known Activations