© 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. 32835
    Prev
    Next
    INDEX
    Explanations

    primary words

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

    controls, distance, primary

    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
    אי
    0.45
     ідэ
    0.45
    ו
    0.44
     ו
    0.44
     되는
    0.44
     까지
    0.44
    awać
    0.44
    阂
    0.43
    는지
    0.42
    cję
    0.42
    POSITIVE LOGITS
     Romanian
    0.51
     primaries
    0.48
     primary
    0.48
     primaire
    0.46
     Kyrgyz
    0.45
     operativos
    0.44
     Afrika
    0.44
     belangrijkste
    0.44
     fréquence
    0.43
     Primary
    0.43
    Activations Density 0.000%

    No Known Activations