© 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. 110682
    Prev
    Next
    INDEX
    Explanations

    backing their products

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

    troubleshooting the JobsDB plugin

    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
     आजादी
    0.55
    Dtls
    0.53
    <unused292>
    0.51
    Brows
    0.50
     دیگه
    0.50
     टाइम्स
    0.49
     میشه
    0.48
     عاوز
    0.48
    ologists
    0.48
     पुणे
    0.48
    POSITIVE LOGITS
     gaping
    0.50
    י
    0.46
     spinal
    0.46
     ventral
    0.44
    洞
    0.44
     stair
    0.43
    わる
    0.43
    мента
    0.42
     Nursing
    0.42
     wahr
    0.42
    Activations Density 0.000%

    No Known Activations