© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 11127
    Prev
    Next
    INDEX
    Explanations

    Vanilla Extract, Mononucleosis (Mono)

    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
    𝐭
    1.58
    𝚏
    1.54
    𝐢
    1.52
    ⓓ
    1.51
    𝐚
    1.44
    ension
    1.43
    tac
    1.42
    𝐫
    1.40
    end
    1.39
    ENSE
    1.39
    POSITIVE LOGITS
     ቅር
    2.04
    অনেক
    2.02
    ময়
    1.98
     uș
    1.88
     StatelessWidget
    1.88
    ષ્ટ
    1.82
     വ്യാപ
    1.79
    unjungi
    1.77
    žd
    1.77
    agic
    1.76
    Activations Density 0.000%

    No Known Activations