© 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. 104865
    Prev
    Next
    INDEX
    Explanations

    bargains, where, visiting, machine, standard, associated

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

    negativity tends to spread

    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
    ြ
    0.54
    ี
    0.49
    Robot
    0.49
    ा
    0.49
    ending
    0.48
    Contacts
    0.48
    a
    0.47
    auks
    0.47
    ა
    0.46
    Minus
    0.45
    POSITIVE LOGITS
     lễ
    0.48
     membro
    0.46
     retractable
    0.44
    toj
    0.42
    닝
    0.42
    |_{\
    0.42
    remeno
    0.42
    혐
    0.42
     ).
    0.41
     depress
    0.41
    Activations Density 0.000%

    No Known Activations