© 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. 86055
    Prev
    Next
    INDEX
    Explanations

    specializes in or involved in

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

    politely declined

    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
    સ્ટ
    0.48
     Виктор
    0.48
    阚
    0.47
    Secondo
    0.47
     kader
    0.47
    емого
    0.47
    والفقار
    0.47
    >'
    0.46
    襷
    0.46
    观测
    0.46
    POSITIVE LOGITS
    लक
    0.46
     Racing
    0.45
     تلك
    0.45
     قصير
    0.44
     Conditioning
    0.43
     inches
    0.43
     conditioning
    0.43
     kayaks
    0.42
     pairs
    0.42
    ta
    0.41
    Activations Density 0.001%

    No Known Activations