© 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. 36555
    Prev
    Next
    INDEX
    Explanations

    index or qualifier

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

    cultural sensitivities and input

    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
     Tether
    0.48
     Prist
    0.45
     Prudential
    0.45
     συνεχ
    0.44
     Hang
    0.43
     Intra
    0.43
    m
    0.42
    周围
    0.42
     vuonna
    0.42
     Vent
    0.41
    POSITIVE LOGITS
    ᱝ
    0.49
     हानि
    0.48
    гән
    0.48
     cunning
    0.47
     पढ़ाई
    0.46
     scores
    0.46
    고사
    0.45
     hồi
    0.45
    ју
    0.44
    グリ
    0.44
    Activations Density 0.000%

    No Known Activations