© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12313
    Prev
    Next
    INDEX
    Explanations

    amino acids

    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
    he
    2.65
    ers
    2.49
    اد
    2.38
    주일
    2.26
     die
    2.21
     mir
    2.20
     καλ
    2.15
    듬
    2.15
    ْر
    2.13
    檚
    2.08
    POSITIVE LOGITS
    មី
    3.01
    𝐳
    2.89
    tenance
    2.88
     veniam
    2.86
     breather
    2.85
    エンス
    2.81
    ിത്ര
    2.80
     useCallback
    2.78
    éros
    2.76
    tio
    2.73
    Activations Density 0.016%

    No Known Activations