© 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. 31469
    Prev
    Next
    INDEX
    Explanations

    numbers and counts

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

    massive underground

    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
    Neutral
    0.48
    ῃ
    0.44
    ight
    0.44
     interfacing
    0.42
     sockfd
    0.41
    house
    0.40
    Besides
    0.39
    ​​
    0.39
    ].)
    0.39
    זו
    0.39
    POSITIVE LOGITS
     derece
    0.56
     втором
    0.54
     этапе
    0.52
     segundo
    0.52
     предпо
    0.51
     كريم
    0.50
     údaj
    0.50
     تاني
    0.49
     пр
    0.49
     пять
    0.49
    Activations Density 0.000%

    No Known Activations