© 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. 69839
    Prev
    Next
    INDEX
    Explanations

    shopping and prices

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

    character archetypes and gritty descriptions

    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
     ಥ
    0.44
    ってきた
    0.42
     బల
    0.42
     equivari
    0.42
     давления
    0.41
     lézards
    0.41
     _____________
    0.41
     abruptly
    0.41
    Ⲃ
    0.41
     करणाऱ्या
    0.40
    POSITIVE LOGITS
    affordable
    0.57
    detailed
    0.52
    details
    0.47
    including
    0.47
    includes
    0.47
     необходимо
    0.47
     affordable
    0.47
    shopping
    0.46
    clientsdetails
    0.46
    clothes
    0.46
    Activations Density 0.000%

    No Known Activations