© 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. 148803
    Prev
    Next
    INDEX
    Explanations

    discussion on

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

    emotional impact or damage

    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
     ميد
    0.57
     железнодоро
    0.57
     لحد
    0.50
    兒
    0.48
    sld
    0.47
     echip
    0.46
     Ι
    0.46
    tten
    0.45
     آبادی
    0.45
     incompetence
    0.43
    POSITIVE LOGITS
    ૃહ
    0.46
     fruity
    0.43
     Tradition
    0.43
    ძლი
    0.42
     ripples
    0.40
     eager
    0.40
     Viejo
    0.40
    喈
    0.39
     fruition
    0.39
    ွှ
    0.39
    Activations Density 0.000%

    No Known Activations