© 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. 12192
    Prev
    Next
    INDEX
    Explanations

    renamed file or computer

    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
     入っ
    0.58
     plufieurs
    0.55
     publicados
    0.55
    𒁲
    0.54
     আরোপ
    0.53
     promul
    0.52
     когда
    0.52
     objeto
    0.52
     accedi
    0.51
     정의역
    0.51
    POSITIVE LOGITS
    an
    0.50
    active
    0.44
    ing
    0.44
    a
    0.43
    ?
    0.43
     Best
    0.43
    å
    0.43
    ta
    0.42
     Leader
    0.42
     Bridge
    0.41
    Activations Density 0.002%

    No Known Activations