© 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. 3665
    Prev
    Next
    INDEX
    Explanations

    constantly, continuously, always

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

    though less

    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
    =
    0.29
    which
    0.28
     които
    0.28
    _
    0.27
    *
    0.27
     ($
    0.27
    2
    0.27
    }
    0.27
     which
    0.27
    [
    0.27
    POSITIVE LOGITS
     meticul
    0.32
     kontinuier
    0.31
     folyam
    0.29
     constamment
    0.29
     berusaha
    0.28
     continuamente
    0.28
     intricately
    0.28
     estremamente
    0.28
     সর্বদা
    0.27
     extremamente
    0.27
    Activations Density 0.000%

    No Known Activations