Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 26262
    Prev
    Next
    INDEX
    Explanations

    instructions, tools, enterprise, examples, tree, people

    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
    at
    0.46
    d
    0.44
    email
    0.42
    Gar
    0.41
    gar
    0.41
    Email
    0.41
    ienne
    0.40
    rms
    0.40
    title
    0.39
    发
    0.39
    POSITIVE LOGITS
     decompositions
    0.47
     algorith
    0.46
     WHICH
    0.45
     incurring
    0.45
     reversing
    0.44
     wou
    0.44
     которы
    0.43
    которы
    0.43
     comptes
    0.42
     который
    0.42
    Activations Density 0.003%

    No Known Activations