© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 24148
    Prev
    Next
    INDEX
    Explanations

    sequences following specific words

    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
     illustrative
    0.40
    }-
    0.39
     illustrating
    0.38
     illustrated
    0.38
     করলাম
    0.38
    電源
    0.38
     ilust
    0.37
     कमजोरी
    0.37
    }{$
    0.36
     demonstrating
    0.36
    POSITIVE LOGITS
    oforte
    0.42
     betracht
    0.41
    Keys
    0.40
     meinen
    0.39
     Thing
    0.37
    醪
    0.37
    ቷ
    0.37
     Queens
    0.36
    долго
    0.36
     Keys
    0.36
    Activations Density 0.000%

    No Known Activations