© 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. 2626
    Prev
    Next
    INDEX
    Explanations

    of the

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

    menu options and console output

    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
     inhibited
    0.48
     $
    0.45
    _
    0.44
    inhib
    0.44
     collectively
    0.42
     stalled
    0.42
     furthermore
    0.41
     forced
    0.41
     </>
    0.41
     captivated
    0.41
    POSITIVE LOGITS
    Defocused
    0.50
     risulta
    0.50
    ITA
    0.49
    Caller
    0.48
     גי
    0.48
    Citation
    0.48
    Course
    0.47
     decisione
    0.47
    เอก
    0.47
    COURSE
    0.46
    Activations Density 0.000%

    No Known Activations