© 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. 15328
    Prev
    Next
    INDEX
    Explanations

    I can, you need, they want

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

    saying "I wanted"

    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
    ів
    0.49
     უფრო
    0.46
     aldrig
    0.44
    ewhere
    0.43
     asla
    0.43
     NEVER
    0.42
    ỷ
    0.41
    }}\
    0.40
    Warum
    0.40
    সমূহ
    0.40
    POSITIVE LOGITS
     saddle
    0.43
    ངས་
    0.42
     lediglich
    0.42
    ન્
    0.41
    欲しい
    0.41
    くれる
    0.41
     wanted
    0.40
     Kult
    0.40
     gând
    0.40
    चौ
    0.39
    Activations Density 0.057%

    No Known Activations