© 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. 64848
    Prev
    Next
    INDEX
    Explanations

    religious and specialized terms

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

    historic city tour

    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
     جانے
    0.47
    ötzlich
    0.47
     треба
    0.47
    葆
    0.44
    voirs
    0.43
     کسی
    0.43
     தேவை
    0.43
    ierter
    0.43
     grammat
    0.42
    ราะห์
    0.42
    POSITIVE LOGITS
    シンプルな
    0.43
     the
    0.41
     outdated
    0.40
     薄
    0.40
     broadly
    0.40
     কার্যক্রম
    0.40
        
    0.40
     ripped
    0.40
     aggressively
    0.40
     protagonista
    0.39
    Activations Density 0.000%

    No Known Activations