© 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. 46720
    Prev
    Next
    INDEX
    Explanations

    margin rules

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

    awkward affairs, difficult chapters, or preclude observation

    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
    т
    0.55
    Т
    0.54
    TE
    0.52
    דו
    0.52
    ס
    0.52
    Typ
    0.51
    Madrid
    0.50
    %");
    0.49
    cómo
    0.49
    С
    0.49
    POSITIVE LOGITS
     gild
    0.55
     lineages
    0.53
     dragons
    0.49
     predators
    0.48
     pathologies
    0.48
     hematopoietic
    0.48
     ligands
    0.47
     singularities
    0.46
     summand
    0.46
     mutants
    0.46
    Activations Density 0.000%

    No Known Activations