© 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. 40-GEMMASCOPE-2-RES-262K
    7. 224273
    Prev
    Next
    INDEX
    Explanations

    major blow, small applications, your body

    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_40_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
    Overflow
    0.47
    icherung
    0.42
    MinIntensity
    0.41
     എ
    0.39
    嫋
    0.39
    溦
    0.39
     ام
    0.39
    ệp
    0.39
    Cher
    0.38
    凧
    0.38
    POSITIVE LOGITS
     parcel
    0.39
    dds
    0.38
     greater
    0.38
     superb
    0.36
    antiate
    0.36
     parcels
    0.36
     Ро
    0.36
     Vision
    0.35
     epidemic
    0.35
     VISION
    0.34
    Activations Density 0.006%

    No Known Activations