© 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. 182205
    Prev
    Next
    INDEX
    Explanations

    this photo, down fall, this title

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

    explaining how something is created

    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
     Planting
    0.57
     Gardening
    0.52
     implantation
    0.49
     Tyler
    0.48
    都知道
    0.48
    ):
    0.46
     অবজার
    0.46
     Everett
    0.45
     Planes
    0.45
     Abt
    0.45
    POSITIVE LOGITS
    ро
    0.54
    らん
    0.54
    r
    0.47
    said
    0.46
    飛ば
    0.46
    mena
    0.46
    RecordPtr
    0.46
    ла
    0.45
    valid
    0.45
    components
    0.45
    Activations Density 0.000%

    No Known Activations