© 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. 185121
    Prev
    Next
    INDEX
    Explanations

    actions and states

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

    technical specifications and information

    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
    బంధ
    0.54
     കർ
    0.51
    VerFile
    0.51
    )”.
    0.50
    Finalmente
    0.49
     ফ
    0.49
    ())){
    0.49
    ኚ
    0.48
     Örneğin
    0.48
     відкри
    0.48
    POSITIVE LOGITS
     be
    0.47
     dau
    0.46
     ain
    0.46
    ≜
    0.44
     hy
    0.43
    ing
    0.42
     felony
    0.42
     mT
    0.42
     variant
    0.42
     tau
    0.42
    Activations Density 0.000%

    No Known Activations