© 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. 193361
    Prev
    Next
    INDEX
    Explanations

    get to

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

    travel and diverse contexts

    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
    р
    0.54
     Mahoney
    0.49
    频
    0.49
    ד
    0.48
    ec
    0.48
    т
    0.47
    兴
    0.47
    es
    0.46
    ab
    0.45
    Hom
    0.45
    POSITIVE LOGITS
     ২০২৩
    0.55
     ২০২২
    0.55
     ২০২০
    0.45
     slows
    0.42
    🩷
    0.42
     අපි
    0.41
    俳優
    0.41
    今回は
    0.41
     tarifas
    0.40
     slowed
    0.40
    Activations Density 0.000%

    No Known Activations