© 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. 133324
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by a noun or verb

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

    building trust and attachments

    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
    }\
    0.49
    Palm
    0.49
     Bend
    0.48
    Bend
    0.48
     Dos
    0.46
    }_
    0.45
     sal
    0.44
     uch
    0.44
    {|
    0.44
    SW
    0.44
    POSITIVE LOGITS
    ürlich
    0.50
    assati
    0.49
    sees
    0.49
    म्मू
    0.48
     ಗ್ರಾ
    0.48
    स्ताव
    0.48
    णाच्या
    0.46
    ges
    0.46
     allant
    0.46
     След
    0.46
    Activations Density 0.000%

    No Known Activations