© 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. 99157
    Prev
    Next
    INDEX
    Explanations

    rental properties

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

    editing and revising text

    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
    вається
    0.54
    接種
    0.45
    ô
    0.45
    ⓡ
    0.43
    劇
    0.43
    dinger
    0.43
    verture
    0.42
    zach
    0.42
    undra
    0.42
    ℗
    0.41
    POSITIVE LOGITS
    Sensor
    0.54
     Sensors
    0.52
    ারন
    0.50
     Smartphones
    0.50
    릎
    0.50
     Posterior
    0.50
    লের
    0.49
     sensor
    0.49
    Ini
    0.48
     yardımcı
    0.48
    Activations Density 0.000%

    No Known Activations