© 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. 194467
    Prev
    Next
    INDEX
    Explanations

    outside of

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

    project navigation and tools

    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
     Bây
    0.47
     Miao
    0.44
    ávan
    0.44
     McCall
    0.43
    (
    0.43
    CLUB
    0.42
     thumbnails
    0.42
    acco
    0.42
     ক্লো
    0.42
    átor
    0.41
    POSITIVE LOGITS
    ༣
    0.55
    pandemic
    0.53
    لاة
    0.51
    мпаваць
    0.49
    utiliser
    0.48
     pagamento
    0.47
    ۶
    0.45
    ༥
    0.45
     திரை
    0.45
    plastic
    0.44
    Activations Density 0.001%

    No Known Activations