© 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. 26629
    Prev
    Next
    INDEX
    Explanations

    this paragraph, yard, week

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

    personality, medication, pieces

    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
     Arlington
    0.50
     Hertfordshire
    0.45
    торию
    0.43
    infrastructure
    0.43
     Radcliffe
    0.42
     сели
    0.41
     Maitland
    0.40
    婷
    0.40
    менно
    0.40
     Holdings
    0.40
    POSITIVE LOGITS
     bool
    0.63
     reward
    0.57
    reward
    0.54
     sprintf
    0.54
     bacter
    0.50
     betterment
    0.49
     joy
    0.48
    bool
    0.48
     improvement
    0.48
     badge
    0.47
    Activations Density 0.000%

    No Known Activations