© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 178250
    Prev
    Next
    INDEX
    Explanations

    ios, SDK

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

    section titles and technical terms

    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
    Negative Logits
    淀
    0.45
     terminations
    0.45
    Sofia
    0.45
     Neg
    0.44
    termin
    0.44
     termina
    0.44
     छोर
    0.44
    HCM
    0.43
    cG
    0.43
     जरिये
    0.42
    POSITIVE LOGITS
    અ
    0.44
    섹
    0.43
     მე
    0.43
    ანს
    0.42
     અમા
    0.42
     professionalism
    0.41
    createStatement
    0.41
     pep
    0.41
     ສ
    0.41
    ಸರ್
    0.41
    Activations Density 0.000%

    No Known Activations