© 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. 202787
    Prev
    Next
    INDEX
    Explanations

    Jonathan Oxford Argentina

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

    quantization or licensing

    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
     funz
    0.59
     chiamato
    0.56
     funzion
    0.55
    ເຮັດ
    0.54
     erhö
    0.52
     menulis
    0.52
    ྰ
    0.51
     poveć
    0.51
    词
    0.50
     svolge
    0.50
    POSITIVE LOGITS
     Jonathan
    0.49
     Oxford
    0.49
    hunter
    0.48
     Argentina
    0.47
     Ebony
    0.47
    hashes
    0.47
     Bhutan
    0.46
    abilidade
    0.46
     Ét
    0.46
    deb
    0.46
    Activations Density 0.000%

    No Known Activations