© 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. 169812
    Prev
    Next
    INDEX
    Explanations

    cost-effective solutions

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

    actions or descriptions followed by details

    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
     వె
    0.48
     décro
    0.45
    Low
    0.43
    Y
    0.43
     fein
    0.43
    дой
    0.42
     Jumbo
    0.42
     ತಿಳಿದ
    0.41
     Widers
    0.41
     Tempt
    0.40
    POSITIVE LOGITS
    ㅃ
    0.52
    ബോ
    0.52
     vua
    0.50
     segmento
    0.48
     negativos
    0.48
    akala
    0.48
     integrar
    0.47
     integrada
    0.47
     consideramos
    0.47
     episodi
    0.47
    Activations Density 0.000%

    No Known Activations