© 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. 175345
    Prev
    Next
    INDEX
    Explanations

    save to

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

    research the emotions

    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
     espress
    0.46
    Herkese
    0.45
     enunci
    0.43
     ресу
    0.43
    Antoine
    0.43
    Farland
    0.43
    捙
    0.43
    р
    0.41
    —”
    0.41
    aurants
    0.41
    POSITIVE LOGITS
    علن
    0.47
    tema
    0.46
     Northeast
    0.46
     complexion
    0.46
     berd
    0.46
    sizeof
    0.46
     poda
    0.45
    ன்னி
    0.45
     undang
    0.45
     tinge
    0.45
    Activations Density 0.000%

    No Known Activations