© 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. 156807
    Prev
    Next
    INDEX
    Explanations

    our website

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

    ladder/game/turbine context; followed by word fragment or continuation

    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
    й
    0.56
    ān
    0.52
    ็น
    0.51
    м
    0.51
    та
    0.50
    sustaining
    0.50
    jší
    0.49
     пі
    0.47
    ｍ
    0.47
    lls
    0.46
    POSITIVE LOGITS
    Oo
    0.50
    Dd
    0.48
     Vanuatu
    0.47
    Fest
    0.47
     bitumen
    0.47
     Steen
    0.46
    Droite
    0.45
    carpeta
    0.45
    Galer
    0.44
    DOUBLE
    0.44
    Activations Density 0.001%

    No Known Activations