© 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. 41909
    Prev
    Next
    INDEX
    Explanations

    newest protocols and terms

    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
    dometer
    0.45
     jurisprudence
    0.40
     Calling
    0.39
     Congress
    0.38
     ማ
    0.38
     Alejandro
    0.37
     कांग्रेस
    0.37
     dubious
    0.37
     字
    0.37
     লি
    0.36
    POSITIVE LOGITS
     verhind
    0.46
     neuen
    0.46
     potenz
    0.46
    Очень
    0.45
     caché
    0.45
    plicht
    0.45
     võimal
    0.44
    ţiile
    0.44
     হিন্দুদের
    0.44
    പ
    0.44
    Activations Density 0.002%

    No Known Activations