© 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. 188911
    Prev
    Next
    INDEX
    Explanations

    publications with volume and page numbers

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

    special characters and specific words

    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
    ,
    0.61
    inger
    0.57
    ern
    0.52
    .
    0.50
    ing
    0.47
    ur
    0.47
    ü
    0.47
    ens
    0.45
    ug
    0.44
    appell
    0.44
    POSITIVE LOGITS
    ﻘ
    0.60
     HOTEL
    0.58
     Hôtel
    0.55
    𝒄
    0.55
    間の
    0.54
    乸
    0.54
     localização
    0.53
     হোটেল
    0.53
     květ
    0.52
    Councillor
    0.52
    Activations Density 0.000%

    No Known Activations