© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 26917
    Prev
    Next
    INDEX
    Explanations

    forms the basis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sigmoid
    0.38
    quilibrium
    0.38
    謗
    0.38
     discouraging
    0.36
     રાહ
    0.36
    昏
    0.36
    诮
    0.36
    ವಹ
    0.35
    dzie
    0.35
    ző
    0.34
    POSITIVE LOGITS
     basis
    1.58
     Grundlage
    1.44
    basis
    1.35
     Basis
    1.29
    Basis
    1.27
     inspiration
    1.26
     основе
    1.25
     основу
    1.14
     underpin
    1.13
     inspirations
    1.06
    Activations Density 0.033%

    No Known Activations