© 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. 86854
    Prev
    Next
    INDEX
    Explanations

    cheapest NAME BRAND

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

    Etruscan and code expressions

    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
     precarious
    0.53
     USDT
    0.52
    ₽
    0.52
     disney
    0.51
     meditate
    0.50
     utterly
    0.50
     anticipate
    0.49
     assayed
    0.49
     м
    0.48
     Una
    0.47
    POSITIVE LOGITS
    änner
    0.49
    iare
    0.45
    ânica
    0.45
    ivia
    0.45
    atus
    0.44
    ütter
    0.44
    issel
    0.44
    ict
    0.43
    amer
    0.43
    uelle
    0.43
    Activations Density 0.001%

    No Known Activations