© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 213449
    Prev
    Next
    INDEX
    Explanations

    of then could

    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
    ucible
    0.39
    ="%
    0.39
     entièrement
    0.39
     ಸೆ
    0.38
    ősz
    0.37
     centering
    0.37
     imposed
    0.37
     जीनत
    0.37
     revêt
    0.37
    Its
    0.36
    POSITIVE LOGITS
    ខ្ល
    0.44
     перено
    0.39
     Madsen
    0.38
    दार
    0.37
    🐬
    0.36
    agles
    0.36
    राधिक
    0.36
    till
    0.36
    rtList
    0.36
    دق
    0.35
    Activations Density 0.001%

    No Known Activations