© 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. 105439
    Prev
    Next
    INDEX
    Explanations

    specified element

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

    key nouns followed by structure

    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
    や
    0.60
    và
    0.55
     veya
    0.47
     או
    0.47
    您
    0.47
    ích
    0.46
    をはじめ
    0.46
    matric
    0.46
    以及
    0.46
    、
    0.46
    POSITIVE LOGITS
     immutable
    0.44
     hypothes
    0.43
     synthesis
    0.43
     nearby
    0.42
     observatory
    0.42
     irreducible
    0.42
     surnames
    0.40
     ages
    0.40
     intuit
    0.40
     proximal
    0.39
    Activations Density 0.003%

    No Known Activations