© 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. 139224
    Prev
    Next
    INDEX
    Explanations

    business, sales, availability, events

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

    sign, is, local, status

    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
    ীণ
    0.52
    梦
    0.50
    ową
    0.49
    ции
    0.48
    羁
    0.48
    完毕
    0.47
    完
    0.47
    ającego
    0.46
    会
    0.46
    宴
    0.46
    POSITIVE LOGITS
    がたくさん
    0.48
     omnip
    0.47
    /}
    0.47
     normalization
    0.46
     devotees
    0.45
     normalizing
    0.44
     conlle
    0.44
     bestseller
    0.44
     fascin
    0.43
     nationalists
    0.43
    Activations Density 0.002%

    No Known Activations