© 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. 22849
    Prev
    Next
    INDEX
    Explanations

    health and professional roles

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

    descriptions of entities and actions

    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
     cheeky
    0.72
     fucking
    0.68
     badass
    0.67
     shitty
    0.67
     underwhelming
    0.64
    🫡
    0.63
     वक़्त
    0.61
    🖕
    0.61
     freaking
    0.61
     fucked
    0.59
    POSITIVE LOGITS
     antik
    0.46
     lighted
    0.45
     birinci
    0.44
     Hanford
    0.44
     pictorial
    0.44
     obiect
    0.43
    
    0.42
     가운데
    0.41
    
    0.41
     materiais
    0.40
    Activations Density 0.021%

    No Known Activations