© 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. 190837
    Prev
    Next
    INDEX
    Explanations

    describing visual attributes and possibilities

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

    monitoring and debugging

    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
     плюс
    0.47
    曛
    0.46
     необходимые
    0.44
     transducers
    0.44
     Jet
    0.43
     необходи
    0.43
    不够
    0.43
     Är
    0.42
     Jakub
    0.42
    不足
    0.41
    POSITIVE LOGITS
    v
    0.55
    nti
    0.54
    root
    0.54
    vl
    0.52
    rti
    0.52
    own
    0.51
    dict
    0.51
    ti
    0.50
    orge
    0.50
    out
    0.49
    Activations Density 0.000%

    No Known Activations