© 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. 31-GEMMASCOPE-2-RES-262K
    7. 12022
    Prev
    Next
    INDEX
    Explanations

    referring to others' words/ideas

    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_31_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
     buildFor
    0.49
    नए
    0.47
    的选择
    0.46
    utile
    0.42
    Thank
    0.42
    That
    0.42
    通过
    0.42
    Լ
    0.42
    为
    0.41
    信息的
    0.41
    POSITIVE LOGITS
     kein
    0.48
     például
    0.48
     esimerkiksi
    0.47
     geen
    0.47
     keine
    0.45
    စ္စည်း
    0.45
     ebenfalls
    0.45
     keinen
    0.44
     zog
    0.43
     eingesch
    0.43
    Activations Density 0.006%

    No Known Activations