© 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. 37776
    Prev
    Next
    INDEX
    Explanations

    spectrometer spectra spectroscopy

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

    privacy concerns information

    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
    imise
    0.46
     shoal
    0.43
     numai
    0.42
    建筑物
    0.42
    通り
    0.41
     மாவட்டத்தில்
    0.41
    塁
    0.41
    📓
    0.41
    }=
    0.41
     viviendas
    0.41
    POSITIVE LOGITS
     Spectra
    0.53
    诸多
    0.49
     Lig
    0.46
     Spect
    0.45
     Thyroid
    0.45
     Aff
    0.44
     LGBTQ
    0.44
     spectra
    0.44
     Orthodox
    0.44
     Uruguay
    0.43
    Activations Density 0.000%

    No Known Activations