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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 573
    Prev
    Next
    INDEX
    Explanations

    Bollinger Bands

    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_13_width_65k_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
    Modified
    1.60
    佻
    1.57
    िला
    1.53
    izr
    1.50
     बिता
    1.48
    クライ
    1.47
    freq
    1.46
    名为
    1.44
    ेंसिल
    1.44
    *********
    1.44
    POSITIVE LOGITS
    তিক্রম
    2.00
    autiful
    1.81
    şiktaş
    1.73
    rawn
    1.69
     anthrac
    1.66
     bunga
    1.59
     عز
    1.52
     Paribas
    1.51
    ardo
    1.50
    azaar
    1.49
    Activations Density 1.129%

    No Known Activations