© 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. 20058
    Prev
    Next
    INDEX
    Explanations

    positive descriptive adjectives

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

    clear explanations/structure

    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
    anning
    0.47
    ojan
    0.45
    unning
    0.43
    /
    0.42
    льной
    0.41
    ann
    0.41
     संबंधी
    0.41
    adihi
    0.41
    ating
    0.40
    犯罪
    0.40
    POSITIVE LOGITS
     dacă
    0.48
     novia
    0.45
     circa
    0.41
     ingresos
    0.40
     tedes
    0.39
     that
    0.39
    似
    0.39
     "%
    0.39
     muros
    0.39
     homelessness
    0.38
    Activations Density 0.003%

    No Known Activations