© 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. 194375
    Prev
    Next
    INDEX
    Explanations

    US States and abbreviations

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

    algorithmic differentiation

    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
     EEA
    0.47
    PPE
    0.46
     дошко
    0.45
    很少
    0.45
     gtag
    0.45
     equivalente
    0.44
    身
    0.43
    दूसरी
    0.43
    巴
    0.43
    㐸
    0.43
    POSITIVE LOGITS
    maker
    0.50
    music
    0.50
    امر
    0.49
    ামি
    0.47
     ತಯಾರ
    0.47
    э
    0.46
    mur
    0.45
     Wilhelm
    0.44
    elect
    0.44
    arev
    0.44
    Activations Density 0.001%

    No Known Activations