© 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. 77079
    Prev
    Next
    INDEX
    Explanations

    illegal and harmful content

    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
     préstamo
    0.42
    绿
    0.40
    quela
    0.39
    কে
    0.39
     बढ़ाकर
    0.39
    赘
    0.39
    琪
    0.38
    P
    0.38
    隐藏
    0.38
    น้อง
    0.38
    POSITIVE LOGITS
    їн
    0.48
     yourself
    0.45
     duly
    0.45
     propellant
    0.44
     inquis
    0.42
     sonore
    0.42
     braz
    0.41
     gripe
    0.41
     chirp
    0.41
     kontroll
    0.40
    Activations Density 0.014%

    No Known Activations