© 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. 194760
    Prev
    Next
    INDEX
    Explanations

    reportformsdeliberationsentirely

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

    medical therapy for SAD

    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
    ந்த
    0.50
    тере
    0.49
    ર
    0.47
    籐
    0.46
    רי
    0.45
    ждению
    0.45
    ילו
    0.45
    िना
    0.44
    רו
    0.44
    σα
    0.44
    POSITIVE LOGITS
    k
    0.62
    muy
    0.54
    kast
    0.52
     jubil
    0.51
    kable
    0.51
     humanist
    0.50
    kta
    0.50
    gui
    0.50
     chatbots
    0.50
     FAL
    0.49
    Activations Density 0.000%

    No Known Activations