© 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. 135727
    Prev
    Next
    INDEX
    Explanations

    past events or states

    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
    에
    0.53
    adapted
    0.48
    Fac
    0.47
    ol
    0.45
    に
    0.45
     Osm
    0.45
    p
    0.45
    s
    0.44
    ريبي
    0.43
     Voices
    0.43
    POSITIVE LOGITS
     непло
    0.49
    mitter
    0.48
    リット
    0.48
     కానీ
    0.48
    тей
    0.48
     reducer
    0.47
    रोध
    0.47
    ረጃ
    0.47
     tempr
    0.46
     blinded
    0.46
    Activations Density 0.003%

    No Known Activations