© 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. 141578
    Prev
    Next
    INDEX
    Explanations

    producing actions or states

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

    based solely

    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
     новий
    0.57
     nowy
    0.52
     ರಾಜ
    0.52
     ಯು
    0.52
     جدید
    0.51
     ദുൽ
    0.50
    नरी
    0.49
    젹
    0.49
     تازه
    0.49
     ಕಂಚ
    0.49
    POSITIVE LOGITS
     producing
    0.44
    f
    0.43
    eth
    0.42
    d
    0.41
    ern
    0.40
    </em>
    0.39
     Producing
    0.39
    s
    0.39
    ified
    0.39
    ed
    0.39
    Activations Density 0.000%

    No Known Activations