© 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. 17261
    Prev
    Next
    INDEX
    Explanations

    get rid of

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

    get rid of / ridges

    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
    椇
    0.37
    ⓝ
    0.37
     అరుణ
    0.37
     React
    0.36
    XmlElement
    0.36
     marina
    0.35
     Delegate
    0.35
    Roxy
    0.35
    芊
    0.35
     reactive
    0.35
    POSITIVE LOGITS
     rid
    3.97
    Rid
    3.84
     Rid
    3.78
     ridge
    3.72
     Ridge
    3.59
    Ridge
    3.48
     RID
    3.44
    rid
    3.41
     ridges
    3.31
    ridge
    3.14
    Activations Density 0.121%

    No Known Activations