© 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. 260095
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     ماحول
    0.49
     umowy
    0.46
     એવી
    0.45
     没有
    0.44
     ink
    0.43
     um
    0.43
     "*");
    0.43
     ከፍተኛ
    0.42
     ambiente
    0.42
     emailing
    0.42
    POSITIVE LOGITS
    ੫
    0.52
    uvre
    0.51
     counterfe
    0.47
    λε
    0.46
    ilie
    0.46
    ਿਲ
    0.46
    ifie
    0.46
    cta
    0.45
    <0xA1>
    0.44
    printf
    0.44
    Activations Density 0.001%

    No Known Activations