© 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. 15810
    Prev
    Next
    INDEX
    Explanations

    cannot be combined with other offers

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

    thread execution and state changes

    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
    יו
    0.51
    ת
    0.50
     אפ
    0.49
    🥺
    0.49
    லாத
    0.49
     שא
    0.48
     असुर
    0.47
    𝘩
    0.46
    ЕН
    0.46
    窅
    0.46
    POSITIVE LOGITS
     amended
    0.52
     Amended
    0.50
     increased
    0.49
     added
    0.46
     revised
    0.45
     moved
    0.44
     improved
    0.44
     Blackhawks
    0.44
     homeowners
    0.43
     folyt
    0.43
    Activations Density 0.002%

    No Known Activations