© 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. 249116
    Prev
    Next
    INDEX
    Explanations

    concepts and descriptions

    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
     разгово
    0.55
    荑
    0.53
     níveis
    0.50
    מ
    0.49
     tumhe
    0.48
    Pog
    0.48
    Gü
    0.48
    کن
    0.47
    כל
    0.47
     francia
    0.47
    POSITIVE LOGITS
    encoder
    0.53
    falls
    0.44
     falls
    0.42
    ulates
    0.41
    !);
    0.40
     ceases
    0.40
    ());
    0.40
    urnal
    0.40
    ខ្សែ
    0.39
     Shil
    0.39
    Activations Density 0.000%

    No Known Activations