© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 239220
    Prev
    Next
    INDEX
    Explanations

    states followed by context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    t
    0.49
    os
    0.37
    because
    0.37
    utiliser
    0.35
    et
    0.35
    sp
    0.33
    teries
    0.33
    enery
    0.33
    resource
    0.32
    cash
    0.31
    POSITIVE LOGITS
     biosynthesis
    0.38
     değil
    0.37
     اپنے
    0.36
    ،
    0.36
     atrophy
    0.36
     Somewhere
    0.35
     epiphany
    0.35
     Acta
    0.35
     implique
    0.35
     relevantes
    0.35
    Activations Density 0.001%

    No Known Activations