© 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. 76649
    Prev
    Next
    INDEX
    Explanations

    specific terms and names

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

    check iffree forall verticesclear and specific

    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
     m
    0.45
    0.44
     departs
    0.43
    in
    0.43
    expressing
    0.43
     Than
    0.42
    P
    0.42
                    
    0.42
     com
    0.41
     chub
    0.41
    POSITIVE LOGITS
    वर्ल्ड
    0.57
     साम्राज्य
    0.55
    手術
    0.53
     всіх
    0.52
    手术
    0.52
     स्थिति
    0.49
     สําหรับ
    0.49
    🩺
    0.48
    เฉพาะ
    0.47
     спорттук
    0.47
    Activations Density 0.000%

    No Known Activations