© 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. 4121
    Prev
    Next
    INDEX
    Explanations

    online services and account management

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

    access, availability, limitations, changes

    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
     শিষ্য
    0.30
     généralement
    0.30
    {\
    0.29
     ObjData
    0.29
     BlueprintName
    0.29
    {\'
    0.29
     GoObject
    0.28
     {\
    0.28
     elementName
    0.28
     OBJECT
    0.27
    POSITIVE LOGITS
     stupid
    0.41
     stupidity
    0.39
    居然
    0.38
    🤬
    0.38
     Expedia
    0.37
     tarifs
    0.36
     Verizon
    0.36
     supposedly
    0.36
     Yahoo
    0.36
    Verizon
    0.36
    Activations Density 0.210%

    No Known Activations