© 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. 191663
    Prev
    Next
    INDEX
    Explanations

    multilingual content

    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
    幕
    0.43
     critics
    0.37
     NORTH
    0.36
    NORTH
    0.36
    ുകൾ
    0.35
     berwarna
    0.35
    <iframe>
    0.34
     slate
    0.34
    WHO
    0.34
     /
    0.34
    POSITIVE LOGITS
    राज्यपाल
    0.47
    म्र
    0.44
    म
    0.44
    aldb
    0.44
     متحدہ
    0.43
    ürdig
    0.43
     инфек
    0.43
     рік
    0.42
    ilación
    0.42
    éma
    0.42
    Activations Density 0.000%

    No Known Activations