© 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. 40-GEMMASCOPE-2-RES-262K
    7. 85025
    Prev
    Next
    INDEX
    Explanations

    csharp code blocks

    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
    ੜ
    0.39
     instante
    0.37
    ior
    0.37
     embar
    0.37
    ains
    0.36
    ება
    0.35
     conclu
    0.35
     demand
    0.35
    オー
    0.35
    ଓ
    0.35
    POSITIVE LOGITS
     несколько
    0.44
    ంచెం
    0.41
    蝶
    0.39
    द्वानी
    0.39
    CITY
    0.38
     ниже
    0.38
    ष्य
    0.37
    </thead>
    0.37
     возвра
    0.37
    ্যে
    0.36
    Activations Density 0.000%

    No Known Activations