© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 203390
    Prev
    Next
    INDEX
    Explanations

    spatial and temporal comparisons

    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
    ྪ
    0.48
    𝗮
    0.47
     끊
    0.44
    𝗰
    0.44
     болез
    0.44
    ocardial
    0.44
    Ка
    0.43
    ő
    0.43
    rå
    0.42
    çe
    0.42
    POSITIVE LOGITS
     treatment
    0.50
     victory
    0.48
     konsep
    0.48
     hermit
    0.48
     innovative
    0.46
     add
    0.45
     hour
    0.45
     warrior
    0.44
     annex
    0.44
     profit
    0.44
    Activations Density 0.007%

    No Known Activations