© 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. 156153
    Prev
    Next
    INDEX
    Explanations

    legal and financial terms

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

    tricky problem details

    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
     propulsion
    0.48
     phonetic
    0.46
     father
    0.46
     MV
    0.46
     betta
    0.44
     code
    0.44
     $$
    0.44
     hubby
    0.44
     tempus
    0.44
     matchup
    0.44
    POSITIVE LOGITS
    களை
    0.49
     اروپا
    0.49
    ெடுக்க
    0.46
     Европы
    0.45
    isini
    0.45
    aissez
    0.44
     एशिया
    0.43
    暧
    0.43
     Еўропы
    0.43
    ByDefault
    0.43
    Activations Density 0.000%

    No Known Activations