© 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. 130863
    Prev
    Next
    INDEX
    Explanations

    Roy followed by names or G. BIV

    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
    EW
    0.41
     tuy
    0.40
    ਾ
    0.40
    idak
    0.38
    mp
    0.37
     kap
    0.37
    iende
    0.37
    MP
    0.37
    ida
    0.37
     persen
    0.36
    POSITIVE LOGITS
     kth
    0.41
    的机会
    0.41
     °,
    0.41
    awcy
    0.40
     الشيطان
    0.40
    '};
    0.40
     ¿
    0.40
     ≠
    0.40
    的公司
    0.39
     stripped
    0.39
    Activations Density 0.000%

    No Known Activations