© 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. 155012
    Prev
    Next
    INDEX
    Explanations

    positive feeling states

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

    shear wall, cute descriptions, what to expect

    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
    टी
    0.48
     adaptés
    0.46
    𝘧
    0.46
    什么时候
    0.44
     Fähigkeiten
    0.44
     posséd
    0.44
    اف
    0.44
    افي
    0.44
     помощь
    0.43
     besitzen
    0.43
    POSITIVE LOGITS
     $$
    0.50
     $+$
    0.50
    $/
    0.48
     other
    0.48
     その他
    0.46
     Goa
    0.46
     altre
    0.46
     Guatemala
    0.45
    acao
    0.45
    付近
    0.45
    Activations Density 0.001%

    No Known Activations