© 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. 234212
    Prev
    Next
    INDEX
    Explanations

    prospective purchasers

    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
     pake
    0.46
    ovalo
    0.42
    鐩
    0.42
    න්ට
    0.41
    }:=\
    0.40
    ूटूथ
    0.40
    电压
    0.40
    परेट
    0.40
    nommen
    0.40
    经历了
    0.40
    POSITIVE LOGITS
    า
    0.55
    know
    0.51
     виконання
    0.50
     KNOW
    0.50
     PROCUREMENT
    0.50
     SEARCH
    0.48
     HANDLING
    0.48
     supervision
    0.48
     കത്തി
    0.48
     Cambodian
    0.48
    Activations Density 0.000%

    No Known Activations