© 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. 43830
    Prev
    Next
    INDEX
    Explanations

    external link

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

    links, numbers, followed by specific input

    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
    〔
    0.46
    木
    0.43
    🥛
    0.42
    els
    0.42
    方式
    0.41
    delivery
    0.41
    designs
    0.41
    days
    0.40
    边缘
    0.40
    '
    0.40
    POSITIVE LOGITS
     enteric
    0.50
     başlat
    0.49
     touristic
    0.48
     internship
    0.47
     anaerobic
    0.46
     mencapai
    0.46
     endoscopic
    0.46
     uptake
    0.46
     episodic
    0.46
     később
    0.46
    Activations Density 0.000%

    No Known Activations