© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 12802
    Prev
    Next
    INDEX
    Explanations

    In one or a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_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
     also
    0.78
     should
    0.76
     withheld
    0.76
    ."],
    0.74
     disliked
    0.74
     rewarded
    0.72
    ίες
    0.72
     allows
    0.72
     piercings
    0.71
    ']['
    0.71
    POSITIVE LOGITS
     nutshell
    1.23
     entrevista
    1.05
     investigación
    1.01
     recent
    0.99
     dystopian
    0.93
     scenario
    0.92
     dunia
    0.88
     saucepan
    0.86
     mundial
    0.86
     بحث
    0.85
    Activations Density 0.019%

    No Known Activations