© 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. 81544
    Prev
    Next
    INDEX
    Explanations

    three things

    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
    amel
    0.49
    ირი
    0.48
    neat
    0.47
    stens
    0.45
    gena
    0.45
    gana
    0.45
    ember
    0.44
    е
    0.44
    єї
    0.44
    verbrauch
    0.43
    POSITIVE LOGITS
     on
    0.47
     selepas
    0.45
     Afgh
    0.44
     Cashback
    0.44
     sonra
    0.42
     after
    0.41
     Yellow
    0.40
     Wight
    0.40
    勖
    0.40
     Describes
    0.39
    Activations Density 0.008%

    No Known Activations