© 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. 31-GEMMASCOPE-2-RES-262K
    7. 79696
    Prev
    Next
    INDEX
    Explanations

    citations and formatting commands

    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_31_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
    0.51
    ∗
    0.44
     Cl
    0.44
     infestation
    0.44
    ?)
    0.43
    ність
    0.43
    ς
    0.42
    య్య
    0.41
    ).(
    0.41
     diuretic
    0.41
    POSITIVE LOGITS
    W
    0.45
    י
    0.45
    ாலிக
    0.44
    ΕΣ
    0.44
     ওয়াস
    0.44
    ed
    0.43
    پ
    0.43
    로부터
    0.43
    에
    0.43
    我
    0.43
    Activations Density 0.004%

    No Known Activations