© 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. 235058
    Prev
    Next
    INDEX
    Explanations

    phone calls

    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
     জনে
    0.56
    ಓ
    0.52
     horror
    0.52
    language
    0.49
    horror
    0.49
     লিখেছেন
    0.47
     Horror
    0.47
    ẖ
    0.46
     Scully
    0.45
     ဒ
    0.44
    POSITIVE LOGITS
     commande
    0.53
     RESPON
    0.45
    emplo
    0.42
    жде
    0.40
    竞争
    0.40
    принима
    0.39
     турган
    0.39
    RESS
    0.39
     responsable
    0.39
    로그
    0.39
    Activations Density 0.001%

    No Known Activations