© 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. 227354
    Prev
    Next
    INDEX
    Explanations

    specific preceding 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
     lesiones
    0.58
     observar
    0.55
     objetos
    0.54
     océ
    0.54
     privacidad
    0.54
     regiões
    0.53
    浐
    0.52
     antigo
    0.52
     atletas
    0.52
     ácidos
    0.51
    POSITIVE LOGITS
    c
    0.64
    poor
    0.55
    ren
    0.53
    department
    0.53
    deg
    0.52
    ice
    0.51
    d
    0.51
    dem
    0.50
    ab
    0.50
    k
    0.49
    Activations Density 0.001%

    No Known Activations