© 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. 54151
    Prev
    Next
    INDEX
    Explanations

    listing specific items or following items

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

    breakdown of

    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
     PRACTICE
    0.48
    Practice
    0.44
    在我
    0.44
     практики
    0.43
    ใบ
    0.41
     adjuvant
    0.41
     листь
    0.40
     ఉ
    0.40
     другими
    0.40
     rispett
    0.40
    POSITIVE LOGITS
    s
    0.55
    creativecommons
    0.50
    q
    0.47
    idth
    0.44
    зы
    0.44
    ked
    0.43
    sentation
    0.43
    })+\
    0.41
    aid
    0.41
    тім
    0.41
    Activations Density 0.000%

    No Known Activations