© 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. 40-GEMMASCOPE-2-RES-262K
    7. 222082
    Prev
    Next
    INDEX
    Explanations

    contrasting low and high

    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/layer_40_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
     protective
    0.41
     Protective
    0.40
     സന്തോഷ
    0.40
    ales
    0.40
    產
    0.39
     Gain
    0.39
     Rentals
    0.39
     smile
    0.38
     smiling
    0.38
     ales
    0.38
    POSITIVE LOGITS
    ¹)
    0.40
    はり
    0.38
    ¦
    0.38
    Arduino
    0.38
    क़्त
    0.37
    jakan
    0.36
    пропетров
    0.36
    ⇓
    0.36
     berwarna
    0.36
    México
    0.36
    Activations Density 0.000%

    No Known Activations