© 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. 201237
    Prev
    Next
    INDEX
    Explanations

    Proven investigatory experience

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

    hinder, other, simple

    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
    os
    0.56
    y
    0.55
    lr
    0.50
    oh
    0.50
    হের
    0.49
    ame
    0.48
    ah
    0.48
    oz
    0.48
    i
    0.48
    lo
    0.47
    POSITIVE LOGITS
    に向
    0.47
     Labrenzia
    0.46
     Jésus
    0.45
    Kiss
    0.45
     heiß
    0.44
     Geißler
    0.44
     Ciência
    0.44
     કહ્યું
    0.43
     figlio
    0.43
     உருவாக்கு
    0.43
    Activations Density 0.000%

    No Known Activations