© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9696
    Prev
    Next
    INDEX
    Explanations

    http get requests

    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_16k_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
    Laravel
    0.51
    ന്ത്രി
    0.47
    Highest
    0.46
    и
    0.46
    денциа
    0.44
     odpowied
    0.43
    entiary
    0.43
    akoti
    0.43
    ƒ
    0.42
    ूट
    0.42
    POSITIVE LOGITS
    HING
    0.48
     distributors
    0.44
    osomes
    0.44
     ಸಂಖ್ಯ
    0.43
    不得
    0.42
     DISTRIBUTION
    0.41
     wing
    0.41
     separators
    0.41
    mfrac
    0.41
     bins
    0.40
    Activations Density 0.062%

    No Known Activations