© 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. 61196
    Prev
    Next
    INDEX
    Explanations

    will deal, enjoyable concepts, the all

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

    difficult emotional states

    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
    ⁩
    0.46
    вался
    0.44
     Fintech
    0.41
     chuyện
    0.40
     gerçekten
    0.40
     Technology
    0.39
    ımda
    0.39
     Education
    0.39
     Álvaro
    0.39
     thuộc
    0.38
    POSITIVE LOGITS
    瘢
    0.55
    agina
    0.49
    ภา
    0.49
    generalized
    0.48
     socalled
    0.48
    RESSION
    0.48
    apparition
    0.48
     armament
    0.48
     계속
    0.47
     disarmament
    0.47
    Activations Density 0.000%

    No Known Activations