© 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. 110331
    Prev
    Next
    INDEX
    Explanations

    amphitheatre

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

    years ago

    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
     Pok
    0.46
     track
    0.44
    erno
    0.43
     ‘
    0.42
     magar
    0.42
    track
    0.41
    pok
    0.40
     cabs
    0.40
    w
    0.40
     ஒ
    0.40
    POSITIVE LOGITS
    TextViewStyle
    0.50
    計劃
    0.49
    خاص
    0.45
     जोड़े
    0.44
     علماء
    0.44
     кла
    0.44
    企業の
    0.44
    ProjectType
    0.44
     складу
    0.44
     Indianapolis
    0.43
    Activations Density 0.001%

    No Known Activations