© 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. 151189
    Prev
    Next
    INDEX
    Explanations

    context clues

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

    in,

    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
     neoplastic
    0.54
     neurologic
    0.52
     neutron
    0.45
    ኞ
    0.44
     terminal
    0.44
     tumorigen
    0.44
     hepatocellular
    0.44
     justiciable
    0.43
    ภั
    0.42
     neurological
    0.42
    POSITIVE LOGITS
    دع
    0.49
    م
    0.49
    وغ
    0.48
    musik
    0.48
    ক্স
    0.47
    gleichen
    0.47
    什么时候
    0.46
    duk
    0.45
    مش
    0.45
    شهر
    0.44
    Activations Density 0.000%

    No Known Activations