© 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. 33933
    Prev
    Next
    INDEX
    Explanations

    music and price

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

    safety, kill, King, AM, bl

    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
    
    0.41
    悩
    0.39
    ിച്ച
    0.39
    harris
    0.39
     avete
    0.38
    っぱ
    0.38
    ма
    0.38
     guava
    0.38
    도
    0.38
    ју
    0.37
    POSITIVE LOGITS
     सम्मानित
    0.44
     ಸಂಸ್ಥ
    0.43
     রাজনৈতিক
    0.43
     সংগীত
    0.43
     সঙ্গীত
    0.42
     సంగీ
    0.41
     Democracy
    0.41
     क्रांतिकारी
    0.41
     ऑर्गेनाइजेशन
    0.41
     খানের
    0.40
    Activations Density 0.000%

    No Known Activations