© 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. 165480
    Prev
    Next
    INDEX
    Explanations

    various connecting phrases

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

    corrections changed to

    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
    -
    0.57
    ந்தோ
    0.46
    и
    0.45
     Amplitude
    0.44
    ਾ
    0.44
     einschließlich
    0.43
    ――
    0.43
    ,-
    0.42
    瑉
    0.42
    ––
    0.41
    POSITIVE LOGITS
     crescente
    0.48
     indipendente
    0.47
     عوامی
    0.45
    sounds
    0.43
    decyd
    0.43
    सायटी
    0.43
    rada
    0.42
    leasing
    0.42
     zdecyd
    0.42
     ডিজ
    0.42
    Activations Density 0.000%

    No Known Activations