© 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. 78500
    Prev
    Next
    INDEX
    Explanations

    related posts of

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

    relationships and ideas

    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
    0
    0.51
    l
    0.45
    file
    0.44
    lens
    0.43
     Zd
    0.42
    Jensen
    0.41
    AI
    0.41
    <0xE7>
    0.41
     }
    0.41
    XZ
    0.40
    POSITIVE LOGITS
    啬
    0.50
    redient
    0.48
    職場
    0.47
    ैसे
    0.47
     láp
    0.46
    avení
    0.46
     hurtful
    0.46
    说过
    0.46
    숨
    0.46
     bởi
    0.46
    Activations Density 0.001%

    No Known Activations