© 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. 11891
    Prev
    Next
    INDEX
    Explanations

    trans porn

    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
     w
    1.36
     who
    1.27
    할
    1.26
    하지만
    1.24
    하게
    1.19
    하세요
    1.19
     im
    1.18
    w
    1.17
    W
    1.17
    ],
    1.17
    POSITIVE LOGITS
    <unused99>
    2.38
    avasena
    2.21
    क्रोश
    2.11
     liqueur
    2.06
     Prisma
    2.06
     luscious
    2.05
    槸
    2.01
     slopes
    1.99
     courbes
    1.99
     Veľ
    1.98
    Activations Density 0.000%

    No Known Activations