© 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. 121542
    Prev
    Next
    INDEX
    Explanations

    predicting phrases

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

    vehicle or travelsconversational data

    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
     devlet
    0.49
    𒌓
    0.49
    ปลี่ยน
    0.48
     varphi
    0.47
     ál
    0.47
     desempeñ
    0.47
     dokładnie
    0.47
     coarsely
    0.47
     divent
    0.46
    coeff
    0.46
    POSITIVE LOGITS
    ιού
    0.46
    ィ
    0.44
     مست
    0.43
     "")
    0.43
    ıs
    0.42
    ване
    0.42
    肓
    0.42
    인트
    0.42
    俎
    0.42
    ition
    0.41
    Activations Density 0.000%

    No Known Activations