© 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. 158657
    Prev
    Next
    INDEX
    Explanations

    English words preceding specific sequels

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

    not defined by

    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
    дія
    0.45
     били
    0.44
    ్రహ
    0.42
    tarea
    0.42
    rowse
    0.42
     inexpensive
    0.42
    0.41
    톄
    0.41
     }
    0.41
     Bil
    0.41
    POSITIVE LOGITS
     সপ্তাহ
    0.49
    Angles
    0.46
     المستقبل
    0.45
    idez
    0.44
    ്യ
    0.44
     Zukunft
    0.44
     revend
    0.43
    ээр
    0.43
    バイス
    0.43
     toekomst
    0.43
    Activations Density 0.000%

    No Known Activations