© 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. 204383
    Prev
    Next
    INDEX
    Explanations

    unique identifiers for keys

    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
     paradise
    0.52
     suspension
    0.44
     ph
    0.42
     constituent
    0.42
     horticultural
    0.42
     Spanish
    0.42
    p
    0.42
     Philippines
    0.41
     mathematics
    0.41
     revelation
    0.41
    POSITIVE LOGITS
    Scalar
    0.48
    Gravity
    0.48
     Vật
    0.48
    Sketch
    0.46
    nehm
    0.45
    Formatting
    0.45
    tywn
    0.45
     चैनलों
    0.45
     člán
    0.44
    )}(
    0.44
    Activations Density 0.000%

    No Known Activations