© 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. 55916
    Prev
    Next
    INDEX
    Explanations

    foreign scripts and phrases

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

    technical, structural, inventive, dimensions, flexible

    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
     dyads
    0.55
    j
    0.51
    \
    0.49
     these
    0.48
    z
    0.46
    _
    0.46
     levels
    0.44
     cures
    0.44
     id
    0.43
    ,
    0.43
    POSITIVE LOGITS
     शैली
    0.53
     આવશે
    0.52
     নির্ম
    0.51
    靕
    0.49
    াইলেন
    0.48
     উঠবে
    0.48
     हस्ता
    0.47
     उष्ण
    0.47
     коми
    0.47
    शरी
    0.46
    Activations Density 0.000%

    No Known Activations