© 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. 141861
    Prev
    Next
    INDEX
    Explanations

    time and activities

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

    systems running smoothly

    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
    デン
    0.46
    Ｎ
    0.43
    ９
    0.43
    ４
    0.42
     Freunden
    0.41
    サイン
    0.41
     seven
    0.41
     slaves
    0.41
    २
    0.40
     originated
    0.40
    POSITIVE LOGITS
    bek
    0.50
     imati
    0.49
    ít
    0.49
    កាន់
    0.48
     ]);
    0.47
                     
    0.47
    អារ
    0.47
     ఉండ
    0.46
     ViewHolder
    0.46
     yö
    0.46
    Activations Density 0.000%

    No Known Activations