© 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. 53075
    Prev
    Next
    INDEX
    Explanations

    everything account inflows stethoscopes

    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
    скім
    0.48
    ække
    0.48
    lical
    0.44
    lectoral
    0.44
    кін
    0.44
     końcu
    0.44
    㳑
    0.44
     конца
    0.43
    ʤ
    0.43
    బంధ
    0.43
    POSITIVE LOGITS
     short
    0.42
     shrunk
    0.42
     insufficient
    0.41
    クライ
    0.39
     steel
    0.38
     fits
    0.38
     suits
    0.38
    Remember
    0.38
     rely
    0.38
     this
    0.37
    Activations Density 0.010%

    No Known Activations