© 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. 142135
    Prev
    Next
    INDEX
    Explanations

    he finds

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

    with his

    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
    ('.
    0.46
     cayó
    0.43
    ቝ
    0.42
    >';
    0.41
    (".
    0.41
    ('',
    0.41
     dueño
    0.41
    aced
    0.40
    }'.
    0.40
    र्टी
    0.40
    POSITIVE LOGITS
     הה
    0.42
    赋予
    0.41
     Rhe
    0.40
     Х
    0.39
     Przed
    0.39
     coexist
    0.39
     Variability
    0.38
     bilateral
    0.38
     Mostly
    0.38
     polyp
    0.38
    Activations Density 0.032%

    No Known Activations