© 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. 109857
    Prev
    Next
    INDEX
    Explanations

    automatic minimum

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

    insult or refund

    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
     వైద్య
    0.48
     nuovi
    0.47
     путь
    0.47
    孀
    0.46
     nuova
    0.44
     hopeless
    0.44
     setempat
    0.44
     varietà
    0.43
    для
    0.43
     nowych
    0.43
    POSITIVE LOGITS
    }")
    0.46
     Asian
    0.44
    ivos
    0.43
     infix
    0.41
    éz
    0.41
     craters
    0.41
    态
    0.41
     IB
    0.40
     Ngọc
    0.40
    }']
    0.40
    Activations Density 0.001%

    No Known Activations