© 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. 211376
    Prev
    Next
    INDEX
    Explanations

    information for investment

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

    explicitly, modular approach, cells themselves

    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
     Pseudomonas
    0.49
     disob
    0.49
    rasse
    0.46
    病情
    0.46
     tumour
    0.46
     melanch
    0.45
    ரது
    0.45
    )}}
    0.43
    ophosph
    0.43
     COPD
    0.43
    POSITIVE LOGITS
    א
    0.49
    어
    0.49
     곳
    0.48
     restrooms
    0.48
     chemins
    0.48
     किंतु
    0.47
    에
    0.47
    🎒
    0.47
     on
    0.46
    Checksum
    0.46
    Activations Density 0.001%

    No Known Activations