© 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. 134016
    Prev
    Next
    INDEX
    Explanations

    collect, retrieve, assess, or predict

    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
    椹
    0.41
     παρα
    0.41
     살펴보도록
    0.40
     গ্রন্থের
    0.39
    穸
    0.37
     alph
    0.36
    ப்பத
    0.36
     cea
    0.36
    改进
    0.36
    鶘
    0.35
    POSITIVE LOGITS
    eer
    0.46
    aise
    0.41
     inflict
    0.40
    destruction
    0.40
     destruction
    0.40
    enched
    0.40
    atement
    0.39
    ateboard
    0.39
    tee
    0.39
    iyot
    0.39
    Activations Density 0.000%

    No Known Activations