© 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. 143723
    Prev
    Next
    INDEX
    Explanations

    endings of sentences

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

    enclosure punctuation

    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
     sterilization
    0.49
    9
    0.48
     confidentiality
    0.47
     sectores
    0.46
    ds
    0.44
     EXECUTIVE
    0.44
    трима
    0.43
    arity
    0.43
    7
    0.43
     precautionary
    0.42
    POSITIVE LOGITS
    Correspond
    0.52
     Gage
    0.51
     limón
    0.50
     colère
    0.48
     convexe
    0.48
     lesión
    0.48
     getToken
    0.47
     medo
    0.46
     найбільш
    0.46
     paura
    0.45
    Activations Density 0.000%

    No Known Activations