© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 27923
    Prev
    Next
    INDEX
    Explanations

    modifications

    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
     non
    0.39
     colored
    0.38
     sixth
    0.37
     symbolic
    0.36
     fed
    0.36
     coloured
    0.36
    顏色
    0.36
    本
    0.36
     escal
    0.35
     hairpin
    0.35
    POSITIVE LOGITS
     modificaciones
    0.42
     modifications
    0.38
     Nipp
    0.38
    ᐉ
    0.38
    ilibre
    0.38
     modificación
    0.38
     Ripp
    0.38
     paroi
    0.37
    züge
    0.37
    зи
    0.36
    Activations Density 0.000%

    No Known Activations