© 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. 20694
    Prev
    Next
    INDEX
    Explanations

    things or negative concepts

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

    big money

    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
    -
    0.46
     Fuerza
    0.45
    BackendAuth
    0.45
    τε
    0.45
     Hampshire
    0.44
     संहिता
    0.44
    kowania
    0.44
     Geno
    0.42
     حزب
    0.42
    捗
    0.42
    POSITIVE LOGITS
    ल्ली
    0.63
     veľmi
    0.51
     velmi
    0.46
    ଳ
    0.46
     început
    0.46
     bursts
    0.46
     imong
    0.46
     stále
    0.46
     útiles
    0.45
     demonstrates
    0.45
    Activations Density 0.000%

    No Known Activations