© 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-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 69391
    Prev
    Next
    INDEX
    Explanations

    owing money or obligations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_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
     tilt
    1.26
     tilted
    1.22
     illuminated
    1.03
     unveiled
    1.01
    ifestyles
    0.98
    ․
    0.98
     Stil
    0.97
     unveils
    0.97
     blocked
    0.96
    arette
    0.95
    POSITIVE LOGITS
     allegiance
    2.72
     maaf
    2.56
    贔
    2.55
    انة
    2.53
    раху
    2.43
    annya
    2.37
     umbilical
    2.37
    맡
    2.36
    rawdę
    2.34
    much
    2.31
    Activations Density 0.000%

    No Known Activations