© 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. 88008
    Prev
    Next
    INDEX
    Explanations

    deletion, negation, or specific elements

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

    non-english or technical terms

    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
    ,’
    0.46
    )[
    0.45
    unan
    0.44
     estar
    0.41
     immaterial
    0.41
    unto
    0.40
    colon
    0.40
    ?’
    0.40
    bran
    0.39
     Sharif
    0.39
    POSITIVE LOGITS
    ផ្ស
    0.52
    ంతరం
    0.49
    ение
    0.47
    ijnlijk
    0.46
    ఐ
    0.46
     குறைக்க
    0.46
     вен
    0.46
    áne
    0.46
     сим
    0.46
    PhysicalDevice
    0.46
    Activations Density 0.006%

    No Known Activations