© 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. 223875
    Prev
    Next
    INDEX
    Explanations

    years ago

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

    both...and

    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
    tı
    0.57
    פתח
    0.55
    אל
    0.51
    tia
    0.50
    t
    0.50
    Ķ
    0.49
    ائیگی
    0.49
     لوبې
    0.49
    Inscription
    0.47
    Ի
    0.47
    POSITIVE LOGITS
     relying
    0.52
     concurs
    0.50
     relies
    0.49
     gras
    0.48
     lowers
    0.47
     buoyant
    0.46
     adds
    0.46
     triggers
    0.46
     floats
    0.46
     precludes
    0.45
    Activations Density 0.000%

    No Known Activations