© 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. 189334
    Prev
    Next
    INDEX
    Explanations

    competencies, foes, passion, translated, wall

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

    ideal scenario or typical price

    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
    Tenemos
    0.49
    瘀
    0.48
    стом
    0.48
    ről
    0.48
    ǜ
    0.47
    rektor
    0.47
    рас
    0.47
    rát
    0.47
    剜
    0.47
    rások
    0.47
    POSITIVE LOGITS
     hardcore
    0.47
    heden
    0.43
     oligonucle
    0.42
     depends
    0.42
     motores
    0.41
     hermaph
    0.41
     plane
    0.41
     moths
    0.41
     hydrodynamic
    0.41
    ্যান্ড
    0.41
    Activations Density 0.001%

    No Known Activations