© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 55979
    Prev
    Next
    INDEX
    Explanations

    conditional phrases like if, not, contains

    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
    TIL
    0.46
    origins
    0.45
     പോക
    0.44
    /-
    0.44
    mystery
    0.44
     regelmäßig
    0.44
     racconto
    0.44
    ī
    0.43
    ும்
    0.42
    /')
    0.42
    POSITIVE LOGITS
     Baseball
    0.41
     Wales
    0.41
     Parti
    0.39
     selfie
    0.39
     Selfie
    0.39
    ினான்
    0.39
     deportivo
    0.38
     Samsung
    0.38
     Newark
    0.38
     Recreation
    0.37
    Activations Density 0.006%

    No Known Activations