© 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. 79456
    Prev
    Next
    INDEX
    Explanations

    distribution platform

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

    subjective descriptions and preferences

    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
     revolutionize
    0.52
     utensils
    0.52
     impeach
    0.52
    ある
    0.50
    โน
    0.49
    OLOGICAL
    0.48
    
    0.48
     および
    0.48
    IZED
    0.48
    гих
    0.48
    POSITIVE LOGITS
     Coil
    0.50
    myn
    0.45
    间的
    0.45
    დომ
    0.44
     Ani
    0.42
     Gathering
    0.41
     Urb
    0.41
     Ivan
    0.40
     Calle
    0.40
    帏
    0.39
    Activations Density 0.001%

    No Known Activations