© 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. 122732
    Prev
    Next
    INDEX
    Explanations

    furniture and descriptive words

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

    than white

    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
    суз
    0.46
     корм
    0.42
     минус
    0.41
     букмекеры
    0.41
     Chimie
    0.40
     препо
    0.40
    蓴
    0.40
    妆
    0.39
     cucumbers
    0.39
    ूली
    0.39
    POSITIVE LOGITS
    ۷
    0.52
     system
    0.49
     quenching
    0.48
    ಡ
    0.48
     verand
    0.45
     systems
    0.45
     prevent
    0.45
     vibrations
    0.45
     protective
    0.45
     projet
    0.44
    Activations Density 0.000%

    No Known Activations