© 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. 115450
    Prev
    Next
    INDEX
    Explanations

    current activity and state

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

    Counterfactual reasoning and explanations

    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
     buttercream
    0.50
     humour
    0.47
     huruf
    0.45
     sahaja
    0.45
     lepas
    0.44
    気が
    0.44
    ິ
    0.44
    搧
    0.43
     Klar
    0.43
     utveck
    0.43
    POSITIVE LOGITS
    controlled
    0.54
    agro
    0.51
    GT
    0.51
    hau
    0.50
    SSC
    0.50
    og
    0.49
    Sob
    0.48
    CS
    0.48
    BLY
    0.47
    }>
    0.47
    Activations Density 0.000%

    No Known Activations