© 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-65K
    7. 65176
    Prev
    Next
    INDEX
    Explanations

    editing text

    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_65k_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
    pubs
    0.43
    ステ
    0.41
    等待
    0.41
     метал
    0.41
    sph
    0.41
     reactant
    0.41
    apellido
    0.41
    ௦
    0.41
    спублі
    0.40
    electrolyte
    0.40
    POSITIVE LOGITS
    编辑
    0.64
     editing
    0.64
    Editing
    0.63
     Editing
    0.63
     editable
    0.61
    editing
    0.58
     edit
    0.54
     Edit
    0.53
     편집
    0.52
     Editable
    0.51
    Activations Density 0.063%

    No Known Activations