© 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. 120651
    Prev
    Next
    INDEX
    Explanations

    head look

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

    claims, Cost, what, existing, loving, snow, appear

    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
    Пло
    0.49
     sadr
    0.46
    夷
    0.45
    פי
    0.43
    Flore
    0.43
    ותו
    0.43
    Stdin
    0.42
    >
    0.42
    സു
    0.42
     niya
    0.41
    POSITIVE LOGITS
     Kubo
    0.46
    但我
    0.46
    granular
    0.45
    2
    0.44
     tentunya
    0.44
     BHP
    0.44
    শ্ম
    0.44
    স্তাফিজ
    0.43
     Henderson
    0.42
     συμφ
    0.42
    Activations Density 0.001%

    No Known Activations