© 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. 7565
    Prev
    Next
    INDEX
    Explanations

    phone numbers

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

    crisis hotlines and safety resources

    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
    }^{*}=\
    0.42
     zbo
    0.40
     ചിത്രം
    0.37
     minded
    0.36
    ennen
    0.35
    woocommerce
    0.35
     methamphetamine
    0.35
    odie
    0.35
    ositol
    0.35
     kost
    0.34
    POSITIVE LOGITS
    百
    0.48
    )-
    0.41
    发挥
    0.40
    írus
    0.38
    BEST
    0.38
     Bye
    0.37
     पूछता
    0.37
    ])-
    0.37
    两大
    0.36
     Unlock
    0.36
    Activations Density 0.040%

    No Known Activations