© 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. 53758
    Prev
    Next
    INDEX
    Explanations

    API access and built incrementally

    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
    ↵↵
    0.49
    sk
    0.46
    ↵
    0.45
    sh
    0.45
     Ch
    0.44
    sm
    0.43
     preposition
    0.43
    chn
    0.42
    Ch
    0.42
    valued
    0.42
    POSITIVE LOGITS
    اویر
    0.55
    ாதாரண
    0.52
    فون
    0.52
     disparo
    0.51
     }=
    0.51
    rául
    0.51
    頨
    0.51
     Eurostile
    0.50
    țit
    0.50
    FOOT
    0.49
    Activations Density 0.001%

    No Known Activations