© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 6984
    Prev
    Next
    INDEX
    Explanations

    photorealistic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_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
     pharmacokinetic
    1.91
    部位
    1.90
     Warzone
    1.88
     sinuses
    1.87
    containers
    1.85
    heden
    1.80
    パーツ
    1.78
    钱
    1.78
    oculars
    1.78
     Vase
    1.78
    POSITIVE LOGITS
     그랬
    1.56
    SSS
    1.51
     그렇
    1.48
    inoa
    1.47
     Cens
    1.46
    罷
    1.45
    entesque
    1.44
    ILIA
    1.42
    impresa
    1.42
    inia
    1.41
    Activations Density 0.007%

    No Known Activations