© 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. 62433
    Prev
    Next
    INDEX
    Explanations

    audition for, invest in, held by, slots of

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

    post-conflict regions

    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
     ἔ
    0.48
     VERS
    0.48
    𒊬
    0.47
    Prote
    0.47
    Subsection
    0.46
     SEQU
    0.46
    Salv
    0.46
    Xiao
    0.46
     Eshelby
    0.46
    íso
    0.45
    POSITIVE LOGITS
     и
    0.47
    :
    0.46
     elke
    0.45
     ولكن
    0.44
    ija
    0.44
     agus
    0.43
     zwar
    0.43
     그래도
    0.42
     varje
    0.42
     mutta
    0.40
    Activations Density 0.000%

    No Known Activations