© 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-262K
    7. 51032
    Prev
    Next
    INDEX
    Explanations

    choices and funds

    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_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
    OUR
    0.50
     vibration
    0.49
    ก
    0.47
    狙
    0.46
    Под
    0.46
    隠
    0.46
    unjungi
    0.44
     waw
    0.44
     فرمان
    0.43
     penchant
    0.42
    POSITIVE LOGITS
    సై
    0.45
    ı
    0.45
     Stelle
    0.44
     Estatal
    0.44
     zich
    0.42
     Ý
    0.42
     adentro
    0.42
     abra
    0.42
    StateException
    0.42
     wykony
    0.42
    Activations Density 0.001%

    No Known Activations