© 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. 157840
    Prev
    Next
    INDEX
    Explanations

    longer periods; Kuwait

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

    Securitization, porous, scale, shipping

    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
     വകു
    0.52
    d
    0.52
    sele
    0.47
    Additional
    0.46
     konusunda
    0.45
     evangel
    0.44
    ike
    0.43
    啓
    0.43
    man
    0.42
     Evangel
    0.42
    POSITIVE LOGITS
    PROCESS
    0.48
    κου
    0.46
     Besitz
    0.45
     délic
    0.44
    ॉन
    0.44
    ającym
    0.44
    㷌
    0.43
     meilleur
    0.43
     réussir
    0.43
    ਔ
    0.43
    Activations Density 0.000%

    No Known Activations