© 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. 209951
    Prev
    Next
    INDEX
    Explanations

    dealing with Stack cake, by

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

    text, instructions, or processes

    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
     deporte
    0.59
     deportes
    0.52
     modalidad
    0.52
     novedad
    0.50
     parola
    0.49
    꾿
    0.49
     canción
    0.48
     empate
    0.48
     apoyar
    0.48
     diferente
    0.47
    POSITIVE LOGITS
    assign
    0.50
    enting
    0.49
    assi
    0.49
    aps
    0.49
    aco
    0.47
    3
    0.45
    techn
    0.45
    atus
    0.43
    atform
    0.43
    anges
    0.43
    Activations Density 0.001%

    No Known Activations