© 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. 59310
    Prev
    Next
    INDEX
    Explanations

    common followed words

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

    lower antelope canyon

    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
     nhanh
    0.51
     rých
    0.50
    ↵↵
    0.47
     vein
    0.47
    一生
    0.47
     rychle
    0.47
     să
    0.46
     první
    0.45
     マーク
    0.44
    聋
    0.44
    POSITIVE LOGITS
    animal
    0.51
    algar
    0.51
    nato
    0.50
    headings
    0.49
    salted
    0.48
    limits
    0.47
    mojo
    0.46
    poem
    0.46
    MIUM
    0.45
    tei
    0.45
    Activations Density 0.001%

    No Known Activations