© 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. 172750
    Prev
    Next
    INDEX
    Explanations

    formal, music, services, title, files

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

    actors, surfactant, scale, firewall

    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
    ര്‍ന്ന
    0.54
    ᶰ
    0.51
     confortable
    0.49
     conval
    0.49
    ORF
    0.48
     Kapol
    0.48
     gespre
    0.47
    ര്‍ന്ന്
    0.47
     reú
    0.47
     tém
    0.46
    POSITIVE LOGITS
    ः
    0.50
     ;
    0.43
    q
    0.41
    炘
    0.41
    atakse
    0.41
    પર
    0.41
    Climate
    0.40
     MESSAGE
    0.40
    Manipulation
    0.40
    स
    0.40
    Activations Density 0.000%

    No Known Activations