© 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. 17682
    Prev
    Next
    INDEX
    Explanations

    foreign languages or specific terms

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

    technical instructions or explanations

    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
     Received
    0.51
     ಸಿನಿಮಾ
    0.51
    н
    0.51
    CEEDINGS
    0.48
    received
    0.46
    р
    0.46
    Received
    0.46
     seconde
    0.46
     recieved
    0.46
     receive
    0.45
    POSITIVE LOGITS
    risque
    0.54
    女の子
    0.45
     Plantation
    0.45
    শুর
    0.44
    ق
    0.44
    kipun
    0.43
    uacute
    0.43
    crit
    0.43
    ilibus
    0.42
     Antônio
    0.42
    Activations Density 0.000%

    No Known Activations