© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 1585
    Prev
    Next
    INDEX
    Explanations

    facebook, hours, info, .png

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

    code keywords if print return

    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
     博文
    0.19
    USER
    0.19
    USERNAME
    0.19
    POST
    0.19
     VERSION
    0.19
     적
    0.18
    nextLine
    0.18
    RIG
    0.18
    Recovery
    0.18
     VARCHAR
    0.18
    POSITIVE LOGITS
    Ꮘ
    0.26
     doubtless
    0.24
     interwoven
    0.24
     hapless
    0.23
    <unused335>
    0.23
     intellectual
    0.23
    <unused1837>
    0.23
     intellectuals
    0.23
     deliverance
    0.22
    <unused307>
    0.22
    Activations Density 0.002%

    No Known Activations