© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 212182
    Prev
    Next
    INDEX
    Explanations

    specific concepts following delimiters

    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
    \@
    0.46
    幹
    0.43
    abe
    0.41
    þ
    0.40
    az
    0.39
    buri
    0.39
    blad
    0.37
    zn
    0.37
     अशी
    0.37
     अब्
    0.36
    POSITIVE LOGITS
     saveData
    0.40
     Saved
    0.40
     savings
    0.38
     momentary
    0.38
     cứu
    0.38
    ᅬ
    0.38
    ້ນ
    0.37
    EVER
    0.37
     goofy
    0.37
     Savings
    0.37
    Activations Density 0.000%

    No Known Activations