© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 116580
    Prev
    Next
    INDEX
    Explanations

    NP-complete

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    y
    0.52
     amoureux
    0.48
    izzato
    0.47
    '
    0.47
     ópt
    0.46
    ùi
    0.45
    ன்
    0.45
     traduc
    0.44
    nal
    0.44
     décor
    0.43
    POSITIVE LOGITS
    )+
    0.62
    大
    0.59
    о
    0.58
    ఎ
    0.56
    }+
    0.54
    }=
    0.53
    কে
    0.51
    Я
    0.50
    co
    0.50
    ak
    0.49
    Activations Density 0.001%

    No Known Activations