© 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. 217099
    Prev
    Next
    INDEX
    Explanations

    plans and offers

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

    specific actions and relations

    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
    "
    0.54
    ng
    0.44
    j
    0.43
     বিকেল
    0.42
    akter
    0.42
     면
    0.42
     shallow
    0.40
     deep
    0.39
     afternoon
    0.39
    bage
    0.39
    POSITIVE LOGITS
     encomendas
    0.59
    බ්
    0.59
     мастеров
    0.54
    󰡕
    0.52
     francesa
    0.52
     Nanjing
    0.51
     Valenc
    0.51
     Elektrokhimiya
    0.50
     homomorphisms
    0.50
     لوبې
    0.49
    Activations Density 0.000%

    No Known Activations