© 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. 6068
    Prev
    Next
    INDEX
    Explanations

    around words like `ago`

    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
    avacan
    0.49
    应当
    0.48
    标题
    0.46
     让
    0.46
    සිය
    0.45
    scientific
    0.45
     എങ്ങനെ
    0.44
     частина
    0.44
     Associ
    0.44
     该
    0.43
    POSITIVE LOGITS
     bore
    0.46
     forcing
    0.42
     roug
    0.42
    枤
    0.42
     falling
    0.41
     cord
    0.41
     stored
    0.41
     blink
    0.40
     fade
    0.40
     string
    0.40
    Activations Density 0.016%

    No Known Activations