© 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-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 3068
    Prev
    Next
    INDEX
    Explanations

    red flag

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PH
    0.60
    মনে
    0.57
    వీ
    0.53
    োহর
    0.51
    oman
    0.51
    q
    0.50
     ringing
    0.49
    bells
    0.48
     V
    0.48
    ర్రీ
    0.48
    POSITIVE LOGITS
    茆
    0.74
    َيْ
    0.65
     ασ
    0.63
     адре
    0.63
     clinic
    0.62
    ιν
    0.61
     তির
    0.61
     мі
    0.61
    ത്താ
    0.61
    Strip
    0.60
    Activations Density 0.181%

    No Known Activations