© 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. 206300
    Prev
    Next
    INDEX
    Explanations

    Analytics, data, questions, addition

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

    detecting fraud, genes, survey, reporting

    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
    bluetooth
    0.58
    iggio
    0.52
    jalan
    0.52
    arin
    0.51
     bluetooth
    0.49
    ினாலும்
    0.48
    ৭
    0.47
    itus
    0.47
     dokt
    0.47
    يلا
    0.47
    POSITIVE LOGITS
     ませ
    0.45
     comerci
    0.45
     παι
    0.44
     cond
    0.42
     ሆ
    0.42
     ever
    0.42
    Cond
    0.42
     clima
    0.41
     মহাশয়
    0.41
    COND
    0.40
    Activations Density 0.000%

    No Known Activations