© 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. 113173
    Prev
    Next
    INDEX
    Explanations

    natural jute

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

    phrases after certain words

    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
     cq
    0.50
     OVER
    0.50
    s
    0.49
     [/
    0.49
    (
    0.46
     flap
    0.45
     addons
    0.44
     ecco
    0.44
     BOARDSIZE
    0.44
    punten
    0.43
    POSITIVE LOGITS
    hamilan
    0.49
    държа
    0.47
    ალაქ
    0.46
     डिसेंबर
    0.45
    icos
    0.45
    絨
    0.45
    狨
    0.45
    astal
    0.44
    anch
    0.43
    aktif
    0.43
    Activations Density 0.000%

    No Known Activations