© 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. 240237
    Prev
    Next
    INDEX
    Explanations

    grounded barriers, congressional law

    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
    ﭘ
    0.49
    "-
    0.47
     unidades
    0.46
    ?-
    0.45
    ()-
    0.45
     litros
    0.45
    蛍光
    0.44
    ாவும்
    0.44
    -{
    0.44
    ïne
    0.43
    POSITIVE LOGITS
     যেসব
    0.46
     Barrier
    0.46
     Ground
    0.45
     Congressional
    0.44
     barrier
    0.43
     congressional
    0.43
    iquement
    0.42
    evich
    0.42
     Law
    0.41
    gebung
    0.41
    Activations Density 0.000%

    No Known Activations