© 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. 89596
    Prev
    Next
    INDEX
    Explanations

    click with / for iphone / Unit testing

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

    completing phrasesor starting sentences

    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
    ključ
    0.36
    сного
    0.34
    郏
    0.33
     fiercely
    0.33
    宣言
    0.33
    FindingsRequest
    0.32
     உட்பட
    0.32
    sadpoetry
    0.32
    franc
    0.32
    謬
    0.31
    POSITIVE LOGITS
     it
    0.36
     playback
    0.31
     κα
    0.30
     και
    0.30
     one
    0.30
     thêm
    0.30
     baking
    0.29
     này
    0.29
     amin
    0.29
     of
    0.29
    Activations Density 0.183%

    No Known Activations