© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11396
    Prev
    Next
    INDEX
    Explanations

    "agg." abbreviation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    𝚞
    2.01
    Alchemy
    1.84
    𝚖
    1.81
     yo
    1.62
     meni
    1.49
    CollectionView
    1.48
    ৰি
    1.46
    ANGE
    1.42
    𝚊
    1.41
    ark
    1.37
    POSITIVE LOGITS
    न
    2.72
    oš
    2.40
    ン
    2.24
    ნიშ
    2.22
    нский
    2.18
    ﺏ
    2.18
    νων
    2.18
    ා
    2.15
    ić
    2.15
    ಿಕ್
    2.14
    Activations Density 0.018%

    No Known Activations