© 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. 126697
    Prev
    Next
    INDEX
    Explanations

    Merchandise sales and email requests

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

    business and finance

    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
    _
    0.55
    thickmathspace
    0.51
    TAC
    0.48
     lenta
    0.48
    PHONY
    0.47
    AnimationClip
    0.46
    FOLD
    0.46
    (=
    0.46
    onChange
    0.45
     勝
    0.45
    POSITIVE LOGITS
     emails
    0.48
     Emails
    0.48
     insures
    0.48
     produ
    0.47
     hoteles
    0.46
     Outfitters
    0.46
     ponto
    0.45
     accompl
    0.44
     estimates
    0.44
    ំន
    0.44
    Activations Density 0.000%

    No Known Activations