© 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. 5288
    Prev
    Next
    INDEX
    Explanations

    don't let X fool you

    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
    잘
    0.85
    शिवाय
    0.80
     বিভ
    0.77
    С
    0.76
     کم
    0.74
    bev
    0.74
     तसेच
    0.73
     잘
    0.73
     nij
    0.72
     nást
    0.71
    POSITIVE LOGITS
     induced
    0.90
     phosphatase
    0.85
     fools
    0.84
    িনে
    0.83
     convulsions
    0.83
     straight
    0.83
     contou
    0.82
     patted
    0.82
     compromised
    0.81
     escorted
    0.81
    Activations Density 0.000%

    No Known Activations