© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 99558
    Prev
    Next
    INDEX
    Explanations

    OS or applications

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

    especially vitamin B

    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
    Во
    0.49
    anvil
    0.47
     услови
    0.46
     transformación
    0.45
     Беларусі
    0.45
    жден
    0.44
    bigr
    0.44
    <unused26>
    0.44
    Ве
    0.44
    ovsk
    0.44
    POSITIVE LOGITS
     hydropon
    0.46
    締め
    0.45
    neze
    0.45
     konkre
    0.45
     Chaos
    0.43
     králov
    0.43
     royal
    0.42
     kü
    0.41
     kuma
    0.41
     mixer
    0.41
    Activations Density 0.000%

    No Known Activations