© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 121366
    Prev
    Next
    INDEX
    Explanations

    common phrases and structures

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

    explaining options or states

    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
     രംഗ
    0.47
     આમંત્રણ
    0.46
    ế
    0.46
    ile
    0.46
    othing
    0.46
    遛
    0.45
    amenti
    0.45
    Diss
    0.44
    "></
    0.44
    ě
    0.44
    POSITIVE LOGITS
     deduced
    0.52
     relays
    0.51
    ួយ
    0.49
     multiplies
    0.48
     pillars
    0.47
     pools
    0.46
    кинуло
    0.46
     fragmentary
    0.46
     seats
    0.46
     rests
    0.46
    Activations Density 0.001%

    No Known Activations