© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 3102
    Prev
    Next
    INDEX
    Explanations

    especially negative situations

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

    social structures and behavior

    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_53_width_65k_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
     тобто
    0.37
    \%.
    0.34
     ossia
    0.34
    ))$.
    0.34
    অর্থাৎ
    0.33
     vendar
    0.32
    ))$,
    0.31
    ))$
    0.31
    authorised
    0.30
    》。
    0.30
    POSITIVE LOGITS
     Especially
    0.45
    especially
    0.42
    Especially
    0.41
    alike
    0.38
     IMHO
    0.38
     especially
    0.38
     बिहारी
    0.38
     खासतौर
    0.37
     woes
    0.37
     khususnya
    0.37
    Activations Density 0.279%

    No Known Activations