© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13170
    Prev
    Next
    INDEX
    Explanations

    fine-tuning models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    </td>
    2.60
    يم
    2.23
     findet
    2.17
    वाने
    2.12
    </th>
    2.10
    Getenv
    2.10
    나라
    2.10
    िनी
    2.09
    حو
    2.07
    ляться
    2.04
    POSITIVE LOGITS
     ld
    2.55
     Jameson
    2.54
    Þ
    2.54
    स्टन
    2.46
     Ryan
    2.42
    ไร
    2.41
     Coul
    2.40
    effer
    2.38
     chieftain
    2.35
    關於
    2.31
    Activations Density 0.093%

    No Known Activations