© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 195555
    Prev
    Next
    INDEX
    Explanations

    stop using, kill the, sales in

    np_acts-logits-general · gemini-2.5-flash-lite

    cult, regulations, defense, strategies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    觟
    0.51
     gamanam
    0.50
    াপাশি
    0.48
     hypothalam
    0.45
     giocare
    0.44
    促
    0.44
     لگا
    0.43
    اداس
    0.43
    拿
    0.43
    Sampler
    0.43
    POSITIVE LOGITS
     pagan
    0.52
     Sug
    0.50
    IDER
    0.50
     feudal
    0.49
     Pagan
    0.48
     cider
    0.48
     declarative
    0.47
    あげ
    0.47
     마을
    0.46
     aliens
    0.46
    Activations Density 0.001%

    No Known Activations