© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 61523
    Prev
    Next
    INDEX
    Explanations

    number and years

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

    changes and states

    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
    ю
    0.48
    v
    0.46
    即使
    0.44
    ة
    0.43
    ък
    0.42
    了一个
    0.42
    予
    0.41
    duration
    0.40
    甚至
    0.39
    ничный
    0.39
    POSITIVE LOGITS
     preth
    0.57
     ܥ
    0.56
     Habsburg
    0.54
     ഏറ്റ
    0.54
    abhavena
    0.53
     นับ
    0.53
     TRANSP
    0.52
     Ches
    0.51
     Portug
    0.50
     rozd
    0.50
    Activations Density 0.000%

    No Known Activations