© 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. 86280
    Prev
    Next
    INDEX
    Explanations

    case, citation, downloads, distribution, material type

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

    comparing AI models

    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
     sequence
    0.47
    gar
    0.44
    agées
    0.44
     identical
    0.43
    l
    0.42
    ँसी
    0.42
     endian
    0.40
    oof
    0.40
    sequence
    0.40
    endtime
    0.40
    POSITIVE LOGITS
     strategie
    0.58
     Foro
    0.58
     Sistemi
    0.55
     Sociales
    0.54
    Categorie
    0.54
     Politique
    0.52
     libertarian
    0.52
     capitalismo
    0.52
    𝙀
    0.51
     علاق
    0.51
    Activations Density 0.000%

    No Known Activations