© 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. 7438
    Prev
    Next
    INDEX
    Explanations

    real city or style

    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
     ზე
    0.48
     після
    0.46
     поз
    0.46
     surpr
    0.44
     እየ
    0.43
    spersed
    0.42
    }^{\
    0.41
     자신
    0.41
     abruptly
    0.41
     स्थल
    0.41
    POSITIVE LOGITS
    0.47
     CITY
    0.46
     real
    0.45
    *
    0.44
     style
    0.44
     City
    0.44
    야
    0.43
     реа
    0.43
     reals
    0.43
     REAL
    0.42
    Activations Density 0.018%

    No Known Activations