© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 14757
    Prev
    Next
    INDEX
    Explanations

    experimental controls and placebos

    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
    ραγ
    1.55
    íticas
    1.51
    lika
    1.50
     konkre
    1.50
     licences
    1.47
    ţa
    1.46
     recognisable
    1.45
    螞
    1.45
    cursors
    1.44
    relationships
    1.44
    POSITIVE LOGITS
     quercetin
    1.47
    DOE
    1.46
    EPA
    1.40
    ER
    1.36
    DMSO
    1.35
     proline
    1.34
    iday
    1.34
     contou
    1.34
     foncé
    1.31
     lotion
    1.31
    Activations Density 0.038%

    No Known Activations