© 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. 14579
    Prev
    Next
    INDEX
    Explanations

    object or object code

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

    object and objectification

    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
     ἐ
    0.72
     be
    0.71
     な
    0.65
     हार्मोन
    0.64
    ATES
    0.60
    oler
    0.59
    ുപത്രി
    0.59
     ὁ
    0.58
     і
    0.57
    ड्डी
    0.57
    POSITIVE LOGITS
     Object
    1.32
     object
    1.21
     objek
    1.16
     objects
    1.05
    object
    1.05
     Objects
    1.02
     OBJECT
    1.02
     objs
    1.02
     Objekt
    1.00
     OBJ
    0.98
    Activations Density 0.026%

    No Known Activations