© 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. 40-GEMMASCOPE-2-RES-262K
    7. 4519
    Prev
    Next
    INDEX
    Explanations

    "include"

    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_40_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
    k
    0.47
    াই
    0.45
     Difference
    0.43
     ঐক্য
    0.42
    amus
    0.42
    差
    0.42
    שר
    0.41
     eingesetzt
    0.41
     mengungkapkan
    0.41
    }$
    0.40
    POSITIVE LOGITS
     provisions
    0.65
     elements
    0.60
     included
    0.59
     therein
    0.59
     incluir
    0.52
     Include
    0.52
     vocals
    0.51
     elementi
    0.51
     stipulations
    0.51
     prerog
    0.50
    Activations Density 0.017%

    No Known Activations