© 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. 165816
    Prev
    Next
    INDEX
    Explanations

    monitor, cooked, them

    np_acts-logits-general · gemini-2.5-flash-lite

    extreme weather events or radiation treatments

    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
    aw
    0.42
     bew
    0.40
    aber
    0.40
     reentry
    0.39
     nanow
    0.39
    '
    0.39
     sor
    0.39
     mechanics
    0.39
     branching
    0.39
     adjudication
    0.39
    POSITIVE LOGITS
     দূরে
    0.55
    cektir
    0.54
     etmektedir
    0.54
    مین
    0.53
    શે
    0.52
    বার
    0.50
    تی
    0.50
    countery
    0.50
    >)`](
    0.50
    embangan
    0.50
    Activations Density 0.000%

    No Known Activations