© 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. 231627
    Prev
    Next
    INDEX
    Explanations

    historical narratives and references

    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
     palliative
    0.50
    軼
    0.43
    rául
    0.42
    ing
    0.41
    itet
    0.40
    andus
    0.40
     就
    0.39
    iatric
    0.39
    alliative
    0.39
     rabbis
    0.39
    POSITIVE LOGITS
    6
    0.50
    3
    0.49
     গবেষণা
    0.46
     httpServer
    0.46
     findAll
    0.45
    
    0.44
    כון
    0.44
     ৪৮
    0.44
    apache
    0.42
     ৩৭
    0.42
    Activations Density 0.001%

    No Known Activations