© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 18520
    Prev
    Next
    INDEX
    Explanations

    recalling conversation history

    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
    বিত্র
    0.46
    ᱗
    0.46
    proxy
    0.43
     vállalat
    0.43
    ᱠ
    0.42
    directory
    0.42
    situation
    0.42
    hostname
    0.42
    Proxy
    0.41
    もっと
    0.41
    POSITIVE LOGITS
     filtrar
    0.44
     pigmented
    0.43
    quela
    0.40
     depender
    0.40
    ikke
    0.40
    ego
    0.39
     filtr
    0.39
    त
    0.39
     lucru
    0.39
     pina
    0.39
    Activations Density 0.001%

    No Known Activations