© 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
    3. 53-GEMMASCOPE-2-RES-65K
    4. 1342
    Prev
    Next
    INDEX
    Explanations

    explaining relationships or concepts

    np_acts-logits-general · gemini-2.5-flash-lite

    write a request for content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ===========
    0.22
    <start_of_image>
    0.21
    <
    0.21
    时不
    0.20
    <blockquote>
    0.20
     =======
    0.20
    ❋
    0.19
    తుంది
    0.19
    艾
    0.19
     <
    0.19
    POSITIVE LOGITS
     Ländern
    0.19
     zehn
    0.18
    <unused995>
    0.18
    ten
    0.18
     Ayrıca
    0.18
    <unused1797>
    0.18
     സമയ
    0.18
     मुसलमान
    0.18
     następnie
    0.18
    ẹ
    0.18
    Activations Density 0.570%

    No Known Activations