© 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. 172302
    Prev
    Next
    INDEX
    Explanations

    former names of people

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

    marketing marketing resistance

    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
     Wiener
    0.51
     What
    0.50
     valore
    0.49
    T
    0.47
     Never
    0.46
     never
    0.45
    D
    0.44
     Love
    0.43
     aldrig
    0.43
     Explain
    0.42
    POSITIVE LOGITS
    뵈
    0.47
    కున్నారు
    0.47
    Hilo
    0.46
    они
    0.46
    LabelTool
    0.45
     контора
    0.45
    CISE
    0.44
    бль
    0.44
    펍
    0.44
    ぶん
    0.44
    Activations Density 0.001%

    No Known Activations