© 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. 36118
    Prev
    Next
    INDEX
    Explanations

    images, ability, new, default, there

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

    sequence or focus

    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
    w
    0.52
     pants
    0.48
    wood
    0.46
    fin
    0.45
    div
    0.45
    m
    0.45
    vi
    0.45
    ail
    0.44
     saddle
    0.44
     Running
    0.44
    POSITIVE LOGITS
     그다음에
    0.48
    StartPreview
    0.47
    _{+}$
    0.46
     क्षतिग्रस्त
    0.45
     meskipun
    0.45
    кугӀ
    0.44
     Fokus
    0.44
    এরপর
    0.44
     автоматтарын
    0.43
    arschijnlijk
    0.43
    Activations Density 0.000%

    No Known Activations