© 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. 33445
    Prev
    Next
    INDEX
    Explanations

    Socket.io, wheel drive, third holiest

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

    explaining technical concepts or code

    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
    律师
    0.53
     недвижимости
    0.51
     обучения
    0.50
     اقتص
    0.49
     основы
    0.49
     καθη
    0.49
    琤
    0.49
     त्रिदेव
    0.48
     கிறிஸ்த
    0.48
     Stéph
    0.47
    POSITIVE LOGITS
     stratosphere
    0.44
     pasture
    0.44
    pared
    0.43
    vol
    0.43
    rm
    0.42
     nears
    0.42
    _
    0.42
    ve
    0.41
    fol
    0.40
    0.40
    Activations Density 0.000%

    No Known Activations