© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5239
    Prev
    Next
    INDEX
    Explanations

    be aware sensitive content

    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
    house
    0.59
     Ital
    0.59
     রো
    0.59
     ఇంటి
    0.58
    Lists
    0.58
     (!
    0.57
     చ
    0.57
    Center
    0.57
     Centro
    0.57
    HOUSE
    0.56
    POSITIVE LOGITS
    bolinks
    0.71
    aconda
    0.67
     proceeded
    0.67
     Ripley
    0.67
     श्रीदेवी
    0.66
     হুঁশিয়ার
    0.66
    ޒ
    0.66
     નાના
    0.63
     குறிப்பாக
    0.63
    ihad
    0.63
    Activations Density 0.070%

    No Known Activations