© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 1681
    Prev
    Next
    INDEX
    Explanations

    text related to locations and geographical details.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz

    of the IBC

    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
    人
    0.27
    x
    0.26
    z
    0.25
    時間
    0.25
     examples
    0.23
     वेगवेगळ्या
    0.22
     levels
    0.22
    生
    0.22
     bouts
    0.21
    ۰۰
    0.21
    POSITIVE LOGITS
     the
    0.34
     this
    0.31
     wannan
    0.30
     της
    0.28
     কাজটি
    0.26
    この
    0.26
     этот
    0.26
     thisobject
    0.25
    The
    0.25
     उक्त
    0.25
    Activations Density 0.664%

    No Known Activations