© 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. 89686
    Prev
    Next
    INDEX
    Explanations

    memorable experience

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

    understanding concepts and reasoning

    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
    噱
    0.61
     تكلم
    0.57
     संय
    0.52
     зро
    0.51
     за
    0.50
     مار
    0.50
    营销
    0.50
    𒂊
    0.50
    橑
    0.50
    )».
    0.50
    POSITIVE LOGITS
     underprivileged
    0.50
     projection
    0.48
    اضره
    0.48
     baik
    0.48
     highway
    0.47
     Guild
    0.47
    ndarray
    0.46
     representation
    0.46
     carboxylic
    0.45
     disadvantage
    0.44
    Activations Density 0.001%

    No Known Activations