© 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. 212776
    Prev
    Next
    INDEX
    Explanations

    state, county, grades, clients

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

    quality, making, inhibitors, designers create, people often

    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
    С
    0.49
     महत्व
    0.48
     resusc
    0.48
     आंखों
    0.48
     воск
    0.48
     energético
    0.46
    すべて
    0.46
    に来
    0.45
    できた
    0.44
    ፑ
    0.44
    POSITIVE LOGITS
    at
    0.52
    change
    0.51
    an
    0.50
     verantwort
    0.50
    heu
    0.50
     verschied
    0.49
    alphabet
    0.49
    maybe
    0.47
    hek
    0.47
    curity
    0.46
    Activations Density 0.003%

    No Known Activations