© 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. 104891
    Prev
    Next
    INDEX
    Explanations

    emphasis or degree

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

    intensifiers and descriptors

    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
    これを
    0.46
     primitives
    0.45
     Infirm
    0.44
     Grunge
    0.44
     bunnies
    0.44
     SHORT
    0.43
     Sham
    0.43
    /
    0.43
    Agreement
    0.43
    Segments
    0.42
    POSITIVE LOGITS
     ખૂબ
    0.48
     rất
    0.46
     вполне
    0.45
     प्रचंड
    0.44
     гораздо
    0.44
     огром
    0.43
    particularly
    0.42
     굉장히
    0.42
    ñada
    0.41
     particularly
    0.40
    Activations Density 0.002%

    No Known Activations