© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 111105
    Prev
    Next
    INDEX
    Explanations

    closest matches and direct relations

    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
     disprove
    0.48
    ಂಜ
    0.42
     reconciled
    0.42
     '</
    0.41
    пе
    0.40
    )}}{\
    0.40
     UIStoryboard
    0.40
     儿
    0.39
     মুহাম্মদ
    0.39
     irure
    0.39
    POSITIVE LOGITS
     दबाव
    0.46
     stratum
    0.44
     recepción
    0.43
     लगाने
    0.41
     fusión
    0.41
     draught
    0.40
     tõ
    0.40
     installation
    0.39
    ダウンロード
    0.39
     Neuron
    0.39
    Activations Density 0.007%

    No Known Activations