© 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. 19129
    Prev
    Next
    INDEX
    Explanations

    future rewards or requirements

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

    maximum that net future created an

    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
     etiquetas
    0.53
     maneras
    0.50
     hairs
    0.49
     acquaintance
    0.48
     coorden
    0.48
    ၡ
    0.48
     pij
    0.47
     encontraron
    0.47
     encontrado
    0.47
    چار
    0.47
    POSITIVE LOGITS
    ’
    0.44
    tele
    0.41
    subsection
    0.41
    prefer
    0.40
    incent
    0.40
    super
    0.39
    behaved
    0.39
    demand
    0.39
     Bellamy
    0.39
    preference
    0.39
    Activations Density 0.000%

    No Known Activations