© 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. 253711
    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
     அறி
    0.46
     Biotechnology
    0.46
     else
    0.46
     Watershed
    0.45
    鉾
    0.45
     acclaimed
    0.44
     Biochemistry
    0.44
     Vivo
    0.43
     ELSE
    0.43
    ermos
    0.43
    POSITIVE LOGITS
     especializados
    0.47
    ɫ
    0.46
     wskaz
    0.44
     molest
    0.44
    ństwo
    0.43
    isierte
    0.42
    écie
    0.42
    áfico
    0.42
    শ্চর্য
    0.42
    )-$
    0.42
    Activations Density 0.000%

    No Known Activations