© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 174054
    Prev
    Next
    INDEX
    Explanations

    phrases like "out trash", "charming and", "life of", "for purchases"

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

    location, on, examples, à, quantum, cause, illness

    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
    USION
    0.45
    दुनिया
    0.44
    תר
    0.42
     Addition
    0.41
    творе
    0.41
    持つ
    0.40
    瓒
    0.40
     autre
    0.40
     addition
    0.39
    Thirty
    0.38
    POSITIVE LOGITS
    geon
    0.52
    ättning
    0.52
     ஈடுப
    0.50
    nrows
    0.50
    橇
    0.49
    aksud
    0.49
     Groningen
    0.48
    Bp
    0.47
    rollo
    0.47
    Unmarshal
    0.47
    Activations Density 0.000%

    No Known Activations