© 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. 217246
    Prev
    Next
    INDEX
    Explanations

    Legal rights and terms

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

    system development and outcomes

    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
    ಾತ
    0.49
    既に
    0.48
    ア
    0.47
    Because
    0.46
    已經
    0.44
    Before
    0.43
    the
    0.43
    As
    0.42
    ラ
    0.42
    ORS
    0.42
    POSITIVE LOGITS
    шёл
    0.48
    sembl
    0.47
     rarement
    0.46
     éché
    0.46
     chute
    0.44
     tâches
    0.44
     pistas
    0.44
    馕
    0.44
     lancé
    0.43
    옳
    0.43
    Activations Density 0.001%

    No Known Activations