© 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. 72947
    Prev
    Next
    INDEX
    Explanations

    body parts or substances

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

    competition, rivalry, cooperation

    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
     sooner
    0.42
     lưu
    0.40
    দৈ
    0.40
     gross
    0.39
    다면
    0.39
    }&=
    0.38
     га
    0.38
     Gunnar
    0.38
    }\|^{
    0.38
     }
    0.37
    POSITIVE LOGITS
     السنوات
    0.49
    🍗
    0.46
    เภท
    0.46
     vremena
    0.45
     Tonawanda
    0.45
     সত্যিকারের
    0.45
    ⭐
    0.45
     مكان
    0.45
    medic
    0.45
     mjest
    0.44
    Activations Density 0.000%

    No Known Activations