© 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. 161827
    Prev
    Next
    INDEX
    Explanations

    completely voluntary

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

    high radius California statement combat

    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
    できました
    0.55
    ი
    0.51
     Địa
    0.49
    윽
    0.49
     था
    0.49
     CommandCenter
    0.49
    ي
    0.48
    तो
    0.47
     خدمة
    0.47
     كانت
    0.47
    POSITIVE LOGITS
    am
    0.47
     psyche
    0.45
    opposition
    0.45
    atu
    0.43
     per
    0.42
    amingo
    0.42
    மையும்
    0.42
    mead
    0.41
     torn
    0.41
     mortal
    0.41
    Activations Density 0.002%

    No Known Activations