© 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. 86547
    Prev
    Next
    INDEX
    Explanations

    sentence start after punctuation

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

    end of sentence punctuation

    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
     கவனம்
    0.46
     її
    0.45
     Europeo
    0.44
    ?!"
    0.43
    ᅲ
    0.43
     توجہ
    0.43
     কারণ
    0.42
     În
    0.42
     Según
    0.42
     ත
    0.42
    POSITIVE LOGITS
     biosolids
    0.44
     structs
    0.43
    рян
    0.41
     eligible
    0.41
    ర్స్
    0.40
     glam
    0.40
    ushed
    0.39
    우스
    0.39
     autochtones
    0.38
    isPrime
    0.37
    Activations Density 0.010%

    No Known Activations