© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8679
    Prev
    Next
    INDEX
    Explanations

    verb + preposition/infinitive

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

    sexual assault hotline

    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
    únior
    0.47
    ]]->
    0.46
    eng
    0.43
    wt
    0.42
    \"",
    0.42
    ha
    0.41
    hm
    0.41
    elas
    0.40
     مُ
    0.40
    Sev
    0.40
    POSITIVE LOGITS
     adenine
    0.83
     ampere
    0.80
    вЂ
    0.58
    ԁ
    0.58
     additionally
    0.56
    曩
    0.55
     conjoint
    0.55
    Ђ
    0.55
     һ
    0.54
     aforementioned
    0.53
    Activations Density 1.480%

    No Known Activations