© 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. 6306
    Prev
    Next
    INDEX
    Explanations

    phrases of the form word followed by another word

    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
    <bos>
    0.96
     nowhere
    0.86
     cheque
    0.77
    anken
    0.74
    ➼
    0.74
     showcase
    0.71
    icen
    0.70
    imon
    0.68
    舗
    0.68
     glace
    0.68
    POSITIVE LOGITS
     सीड्स
    0.93
     చేపట్ట
    0.88
    Integr
    0.82
    勍
    0.81
     harmonics
    0.81
     Integrative
    0.81
    Fermi
    0.80
     बुरी
    0.79
     Abrams
    0.78
     idiot
    0.77
    Activations Density 0.000%

    No Known Activations