© 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. 204472
    Prev
    Next
    INDEX
    Explanations

    compensation and employment terms

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

    online processing and named entities

    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
     smoked
    0.40
     (!)
    0.40
    !
    0.40
     هم
    0.40
     cu
    0.39
     smoky
    0.39
     tadi
    0.39
    itars
    0.38
     হাঁ
    0.36
     cheap
    0.36
    POSITIVE LOGITS
    краё
    0.48
    Რ
    0.46
     शैक्षणिक
    0.46
    তাহ
    0.45
    㺫
    0.44
     주제
    0.42
    दर्शन
    0.42
    Dónde
    0.42
    IDENTAL
    0.41
     calificaciones
    0.41
    Activations Density 0.002%

    No Known Activations