© 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. 895
    Prev
    Next
    INDEX
    Explanations

    DOIs and academic links

    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
     ضمان
    0.37
    秘书
    0.36
    لوث
    0.36
    喿
    0.36
    跇
    0.36
    गेशन
    0.35
     anal
    0.35
    Ⲙ
    0.35
     போக்குவரத்து
    0.35
    𐰤
    0.35
    POSITIVE LOGITS
    apache
    0.58
    1
    0.55
    springframework
    0.53
    slf
    0.47
    ncbi
    0.44
    5
    0.44
    zal
    0.43
     Springer
    0.42
    0
    0.42
    w
    0.42
    Activations Density 0.000%

    No Known Activations