© 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. 187982
    Prev
    Next
    INDEX
    Explanations

    methodical availability

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

    biological and scientific terms

    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
     deta
    0.57
     אפ
    0.50
     tones
    0.47
     rok
    0.47
     उपायों
    0.47
    返
    0.47
    formations
    0.46
    劭
    0.46
    gende
    0.46
    ellers
    0.45
    POSITIVE LOGITS
    ILIO
    0.58
     maliciously
    0.55
    ANU
    0.50
     magnetically
    0.47
    ৩৬
    0.45
    ৩২
    0.44
     accommodate
    0.44
     biologically
    0.43
     livro
    0.43
    শরীর
    0.43
    Activations Density 0.001%

    No Known Activations