© 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. 33736
    Prev
    Next
    INDEX
    Explanations

    potentially competitive threat

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

    predicting controlling media networks

    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
     Crore
    0.49
     村
    0.47
     Wolfgang
    0.46
     忄
    0.45
     ಅದನ್ನು
    0.45
    范围内
    0.45
     crocodile
    0.45
     saree
    0.44
    Ģ
    0.43
     کرکے
    0.42
    POSITIVE LOGITS
     eins
    0.52
    macht
    0.49
    tap
    0.48
    enumValues
    0.46
     expr
    0.45
    ه
    0.45
    unknown
    0.45
    trunc
    0.45
    negoti
    0.45
    Wey
    0.44
    Activations Density 0.001%

    No Known Activations