© 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. 6619
    Prev
    Next
    INDEX
    Explanations

    bullet points

    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
     degeneracy
    0.22
    😿
    0.21
     hadron
    0.20
    StartIndex
    0.19
     sovere
    0.19
    Cols
    0.19
    graphHead
    0.18
     explosions
    0.18
     heuristics
    0.18
     anarchy
    0.18
    POSITIVE LOGITS
    า
    0.23
    ina
    0.22
    ada
    0.21
    ado
    0.21
    ı
    0.21
    ovan
    0.21
    oma
    0.21
     a
    0.21
     यह
    0.20
    也就是说
    0.20
    Activations Density 0.436%

    No Known Activations