© 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. 135719
    Prev
    Next
    INDEX
    Explanations

    words or phrases for guidance

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

    non-English words

    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
    п
    0.45
     orientation
    0.43
     glands
    0.43
     analogs
    0.42
     અનુ
    0.42
     Mot
    0.42
     behavi
    0.41
     für
    0.41
    Fle
    0.41
    ड्डा
    0.41
    POSITIVE LOGITS
     köy
    0.46
    =[]
    0.46
    '}$
    0.45
     varsa
    0.44
    udarstvennyj
    0.43
    avkh
    0.43
    substring
    0.43
    arnataka
    0.43
    pstmt
    0.41
    imbabwe
    0.41
    Activations Density 0.001%

    No Known Activations