© 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. 35326
    Prev
    Next
    INDEX
    Explanations

    events and details

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

    increase and specific training

    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
    altered
    0.55
    encher
    0.53
    arter
    0.52
    removed
    0.52
    role
    0.52
    eker
    0.52
    spa
    0.52
    s
    0.52
    allocate
    0.51
    suggest
    0.51
    POSITIVE LOGITS
     anisotropy
    0.48
     patterning
    0.46
     bakt
    0.46
     polygon
    0.46
     triangles
    0.46
     complexes
    0.46
     anisotropic
    0.43
     prostaglandins
    0.43
     eddies
    0.43
     polygons
    0.43
    Activations Density 0.000%

    No Known Activations