© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77283
    Prev
    Next
    INDEX
    Explanations

    numbers and ordinals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ּוֹ
    -1.11
    痛い
    -1.09
     бампер
    -1.07
    NOTIFY
    -1.02
    ҉
    -0.97
    called
    -0.96
    恥ず
    -0.95
    fören
    -0.94
    ַּ
    -0.92
    före
    -0.92
    POSITIVE LOGITS
     invariably
    1.06
     ostensibly
    1.02
     presumably
    1.02
     zwierząt
    1.01
     potentially
    1.00
     گیاه
    0.99
     principally
    0.96
     unequivocally
    0.92
     evidently
    0.91
     people
    0.89
    Activations Density 0.001%

    No Known Activations