© 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. 186197
    Prev
    Next
    INDEX
    Explanations

    various specific words followed by common words

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

    check and well

    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
    новая
    0.44
    シ
    0.43
    Бар
    0.43
    Как
    0.43
    ル
    0.42
    𝘮
    0.42
     DESIGN
    0.41
    Include
    0.41
    שי
    0.41
    У
    0.41
    POSITIVE LOGITS
    在北京
    0.49
     (!)
    0.47
     durante
    0.45
     قصير
    0.45
     precipit
    0.45
     haberse
    0.45
     studente
    0.45
     Justus
    0.44
     hispanic
    0.44
     bronchitis
    0.44
    Activations Density 0.001%

    No Known Activations