© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 17726
    Prev
    Next
    INDEX
    Explanations

    concepts of importance and motivation

    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
     Na
    0.48
    Na
    0.48
     Ra
    0.46
    j
    0.46
    lev
    0.45
    ロス
    0.45
    騙
    0.45
    <0xB5>
    0.45
    ون
    0.45
    så
    0.45
    POSITIVE LOGITS
     Einstellung
    0.51
     alignItems
    0.49
    ებმა
    0.46
    }|^{
    0.45
     بیوی
    0.45
    }\|^{
    0.45
     erfolgreich
    0.44
    thorace
    0.43
    importanza
    0.43
     successo
    0.43
    Activations Density 0.002%

    No Known Activations