© 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. 139784
    Prev
    Next
    INDEX
    Explanations

    actions and states

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

    structure, dimension, disruption, manufactured

    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
    摒
    0.47
     unison
    0.47
     incrementar
    0.45
     cistern
    0.45
     that
    0.44
     translational
    0.42
     investigating
    0.42
     pathogenesis
    0.42
    च
    0.41
    that
    0.40
    POSITIVE LOGITS
    Պ
    0.49
    Financial
    0.48
    Shiny
    0.48
    Kaynak
    0.47
    Rue
    0.47
    Ý
    0.47
    Ups
    0.46
    ऑन
    0.46
    onnay
    0.46
    Bare
    0.46
    Activations Density 0.002%

    No Known Activations