© 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. 109381
    Prev
    Next
    INDEX
    Explanations

    acronyms and specific terms

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

    `access` `briefly` `resolving`

    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
    Granted
    0.46
    细节
    0.45
    Joining
    0.44
    说是
    0.44
    掺
    0.42
    Already
    0.42
    GEST
    0.41
    نجليزية
    0.41
    SAM
    0.41
    ურთ
    0.40
    POSITIVE LOGITS
     tathapi
    0.45
     australia
    0.44
     নোট
    0.44
     america
    0.44
    स्ड
    0.44
     wildlife
    0.43
    thapi
    0.43
     racem
    0.43
    咽
    0.43
    iversary
    0.42
    Activations Density 0.001%

    No Known Activations