© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72995
    Prev
    Next
    INDEX
    Explanations

    code, Redis, angioplasty, number

    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_22/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
    ('.');
    -1.16
    signable
    -1.15
    ise
    -1.09
    __;
    -1.04
    
    -1.03
    tovat
    -1.02
     vro
    -1.02
    ՚
    -1.01
    %%%%%%%%%%
    -1.01
     prendre
    -1.00
    POSITIVE LOGITS
     any
    0.98
    橢
    0.90
     and
    0.90
     climático
    0.87
    눔
    0.86
    んびり
    0.85
     zahlreiche
    0.84
    大学の
    0.83
    ฟัง
    0.82
    をもって
    0.82
    Activations Density 0.037%

    No Known Activations