© 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-16K
    7. 12612
    Prev
    Next
    INDEX
    Explanations

    default values or configurations

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

    configuration parameters

    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_16k_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
     steered
    0.44
     doesn
    0.43
    iological
    0.43
    boundingRect
    0.39
     amalgamated
    0.39
     Gould
    0.39
     theology
    0.38
    )|^
    0.38
     wouldn
    0.38
     Dyed
    0.38
    POSITIVE LOGITS
    DEFAULT
    0.60
    MAX
    0.52
     MAX
    0.52
     DEFAULT
    0.51
    CONSTANT
    0.49
    SEPARATOR
    0.48
    STANDARD
    0.47
     estándar
    0.47
     PREFIX
    0.47
     SMALL
    0.45
    Activations Density 0.009%

    No Known Activations