© 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. 90722
    Prev
    Next
    INDEX
    Explanations

    stanzas, Tesla, deploying, Rats, PDF

    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
    in
    0.57
    notin
    0.47
    bl
    0.46
    r
    0.45
     prez
    0.45
     AR
    0.44
    ttt
    0.43
     amplia
    0.43
    yim
    0.43
     Tugas
    0.43
    POSITIVE LOGITS
     chromatography
    0.50
    憶
    0.48
    üyor
    0.47
     پوکر
    0.46
    𝟬
    0.46
     causas
    0.45
    侬
    0.45
    achlor
    0.44
     highlighting
    0.44
    াক
    0.44
    Activations Density 0.000%

    No Known Activations