© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 59224
    Prev
    Next
    INDEX
    Explanations

    indirect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    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
     என்பதற்கு
    0.38
    Equatable
    0.38
     ফে
    0.37
    寂
    0.37
    heng
    0.36
     continent
    0.36
     thermoplastic
    0.36
    唬
    0.36
    ᓕ
    0.36
    Nes
    0.36
    POSITIVE LOGITS
     indirect
    3.94
     Indirect
    3.84
    Indirect
    3.77
    indirect
    3.67
     indire
    3.53
     indirectly
    3.52
     INDIRECT
    3.30
     pośred
    1.59
     direct
    1.17
    Direct
    1.08
    Activations Density 0.006%

    No Known Activations