© 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. 201060
    Prev
    Next
    INDEX
    Explanations

    rapidly changing or emerging

    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
     shaft
    0.44
     fencing
    0.42
     heightened
    0.42
     peut
    0.41
     probe
    0.41
     puede
    0.40
    何
    0.40
     sheriff
    0.40
     miners
    0.39
     riparian
    0.39
    POSITIVE LOGITS
     indispens
    0.47
     asymptote
    0.46
     ایمان
    0.45
    practical
    0.45
    astotal
    0.44
    mlst
    0.44
     impuls
    0.44
     관심
    0.44
    ඖ
    0.44
     asympt
    0.44
    Activations Density 0.005%

    No Known Activations