© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 65120
    Prev
    Next
    INDEX
    Explanations

    the concept of understanding

    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
    Donc
    0.49
    arzt
    0.43
    ಿದ್ದು
    0.42
    }_{+
    0.41
     Donc
    0.41
    ă
    0.40
     quindi
    0.39
    ೀವ
    0.39
    m
    0.38
    ($
    0.38
    POSITIVE LOGITS
     lighting
    0.47
    ̊
    0.46
    lighting
    0.44
    鳃
    0.44
     lamin
    0.43
    onation
    0.42
     curbing
    0.42
     terminations
    0.42
     மாணவர்கள்
    0.41
    сия
    0.41
    Activations Density 0.002%

    No Known Activations