© 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. 183542
    Prev
    Next
    INDEX
    Explanations

    employment period, cabinet hardware, moral turpitude, favorable climate

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

    programming prevents

    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
    amantha
    0.52
    adım
    0.49
    Rq
    0.47
    amı
    0.47
     próp
    0.46
    ভ
    0.46
    拥有
    0.46
    💉
    0.46
    ২১
    0.45
    hm
    0.45
    POSITIVE LOGITS
     dirig
    0.47
     Catawiki
    0.45
    มอบ
    0.42
     Gestaltung
    0.42
     അന
    0.42
     カット
    0.42
     می‌تواند
    0.41
    斃
    0.41
    ará
    0.40
     අප
    0.40
    Activations Density 0.001%

    No Known Activations