© 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. 174086
    Prev
    Next
    INDEX
    Explanations

    loves, enhance, pushing, factors, left, hair

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

    exploring concepts with 🤔

    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
     benefactor
    0.48
     stoichiometric
    0.46
    ДУ
    0.45
    QRST
    0.44
     responder
    0.44
     거죠
    0.44
    찮
    0.44
     recib
    0.42
    ቐ
    0.42
     pensioner
    0.41
    POSITIVE LOGITS
    in
    0.51
    avenir
    0.51
    u
    0.50
    ative
    0.49
    riched
    0.49
    oval
    0.48
    ove
    0.46
    ত্যাগ
    0.46
     samot
    0.46
    aughan
    0.46
    Activations Density 0.001%

    No Known Activations