© 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. 229222
    Prev
    Next
    INDEX
    Explanations

    recent developments

    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
    น
    0.57
     downtime
    0.56
    Additionally
    0.52
    తీ
    0.49
     scoot
    0.49
     وارد
    0.48
     lockout
    0.48
    د
    0.48
     Additionally
    0.48
     nuance
    0.47
    POSITIVE LOGITS
    ってる
    0.50
    taobao
    0.50
    ającej
    0.49
    ikir
    0.49
    esquerdo
    0.47
    čnog
    0.46
     certeza
    0.46
    encja
    0.46
    反
    0.46
     قی
    0.45
    Activations Density 0.000%

    No Known Activations