© 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. 165720
    Prev
    Next
    INDEX
    Explanations

    and what

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

    redundant or vague phrases

    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
    folios
    0.45
     ரஷ்ய
    0.45
     ಗುಣ
    0.44
     menggambarkan
    0.44
    ractic
    0.43
     Yugoslavia
    0.43
    }-(\
    0.43
     resul
    0.43
     Cual
    0.42
     dhamm
    0.41
    POSITIVE LOGITS
    '
    0.53
    USE
    0.50
    一
    0.48
    Dir
    0.46
    _
    0.46
    在
    0.46
    Donor
    0.45
    ת
    0.45
    Wood
    0.44
    Probability
    0.44
    Activations Density 0.001%

    No Known Activations