© 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. 146001
    Prev
    Next
    INDEX
    Explanations

    actions and states

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

    places and things

    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
    control
    0.49
    controller
    0.49
     controlador
    0.47
    throttle
    0.45
    晚餐
    0.45
    ובה
    0.45
    receptor
    0.45
    托
    0.44
    coefficient
    0.43
    เท้า
    0.43
    POSITIVE LOGITS
     kaleidos
    0.53
     dominions
    0.52
     chacun
    0.50
     meadows
    0.46
     hadir
    0.46
     enshrined
    0.46
     enshr
    0.46
     jährlich
    0.45
     jähr
    0.45
     jullie
    0.44
    Activations Density 0.001%

    No Known Activations