© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 7170
    Prev
    Next
    INDEX
    Explanations

    concluding transitional contrasting phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    CD
    1.03
     CD
    0.96
     Эта
    0.93
     där
    0.93
     V
    0.89
     Ο
    0.87
    »;
    0.87
    ');
    0.87
     G
    0.85
    ○○
    0.84
    POSITIVE LOGITS
     anyway
    3.31
     anyhow
    2.94
     understandably
    2.93
    speaking
    2.92
     legitimately
    2.92
     unwittingly
    2.88
    ifiably
    2.84
     subconsciously
    2.72
     conceivably
    2.71
     anyways
    2.70
    Activations Density 0.046%

    No Known Activations