© 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. 146335
    Prev
    Next
    INDEX
    Explanations

    computational and scientific concepts

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

    customer relationship management (CRM)

    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
    a
    0.58
    ਸ
    0.56
    娜
    0.51
    스
    0.49
    مركز
    0.48
    。。
    0.48
    دو
    0.48
    intérêt
    0.48
    न
    0.48
    ه
    0.47
    POSITIVE LOGITS
     calibration
    0.49
     computations
    0.49
     absorbance
    0.48
     invariance
    0.48
     sedimentary
    0.48
     computational
    0.47
     methodological
    0.47
     dimensionality
    0.47
     gaussian
    0.47
     thermodynamic
    0.46
    Activations Density 0.001%

    No Known Activations