© 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. 152074
    Prev
    Next
    INDEX
    Explanations

    ; suppose. supposeyou have tocharge particlesyour networkface,:learnt no matter

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

    removing filler words and vague phrasing

    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
     cocina
    0.56
    т
    0.53
     fridge
    0.52
    קו
    0.52
     armario
    0.50
    ㎥
    0.50
     arriba
    0.49
     moto
    0.48
    出来る
    0.48
     vegetal
    0.48
    POSITIVE LOGITS
    Centers
    0.45
    setEnabled
    0.43
    essive
    0.43
    赂
    0.43
    }=(\
    0.43
    enged
    0.42
    entered
    0.42
     Centers
    0.41
     Trainer
    0.41
     Wid
    0.40
    Activations Density 0.000%

    No Known Activations