© 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. 45618
    Prev
    Next
    INDEX
    Explanations

    lists and categories

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

    errors and risks

    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
     afflicted
    0.45
     orient
    0.44
     an
    0.42
     prodig
    0.41
     incriminating
    0.41
    АТО
    0.41
    ¬
    0.41
     coincident
    0.40
     Thir
    0.40
     exc
    0.40
    POSITIVE LOGITS
    計劃
    0.52
    を使う
    0.52
     ትንሽ
    0.52
    簡單
    0.50
    '){$
    0.50
     எளி
    0.49
     महत्त्वा
    0.49
     সহজে
    0.48
    сування
    0.48
    好吃
    0.48
    Activations Density 0.000%

    No Known Activations