© 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. 248661
    Prev
    Next
    INDEX
    Explanations

    entertained enough, better covenant, DNA tests

    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
     fert
    0.60
    ≦
    0.47
     uncomfortable
    0.45
     beaches
    0.45
     heterosexual
    0.44
     erotic
    0.44
     rocks
    0.43
    ToPointer
    0.43
     फर
    0.43
     August
    0.42
    POSITIVE LOGITS
    commentaire
    0.45
    Siempre
    0.44
     ආර
    0.43
    LinkForm
    0.43
     BorderRadius
    0.43
    )\|
    0.43
     அறிவியல்
    0.43
    membre
    0.42
    בש
    0.42
     ಬೆಂಗಳ
    0.42
    Activations Density 0.000%

    No Known Activations