© 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. 188770
    Prev
    Next
    INDEX
    Explanations

    one of the

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

    addition, analytics, social media

    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
    NEW
    0.49
    ，
    0.44
    ▪
    0.43
     સામે
    0.42
    Pod
    0.42
    Failed
    0.42
    FAILED
    0.42
    യ്ക്ക
    0.41
    同时
    0.40
     Brus
    0.40
    POSITIVE LOGITS
     thèse
    0.44
     krijg
    0.44
     '\''
    0.44
    anjian
    0.43
     取っ
    0.43
     maart
    0.43
     ':'
    0.43
     सितम्बर
    0.42
     کرام
    0.42
    hij
    0.42
    Activations Density 0.000%

    No Known Activations