© 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-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 3224
    Prev
    Next
    INDEX
    Explanations

    static method declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    1.13
    O
    1.12
    I
    1.05
     I
    1.01
    T
    0.96
    A
    0.96
    (
    0.93
    al
    0.91
    2
    0.90
    S
    0.88
    POSITIVE LOGITS
    б
    1.04
    п
    1.00
    𝘬
    0.98
    к
    0.94
    त
    0.93
    ма
    0.89
    н
    0.88
    м
    0.86
     он
    0.85
     импе
    0.85
    Activations Density 0.010%

    No Known Activations