© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3944
    Prev
    Next
    INDEX
    Explanations

    "che" followed by verbs or pronouns

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

    rape, abuse, incest, RAINN

    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
    Tart
    0.40
    started
    0.40
    organe
    0.39
     KIR
    0.39
     kirk
    0.37
     ভীষণ
    0.37
    áře
    0.37
     キ
    0.36
     حقیقت
    0.36
    Cle
    0.36
    POSITIVE LOGITS
     ci
    0.67
     si
    0.65
     ti
    0.54
     è
    0.54
     Ci
    0.52
     proviene
    0.52
    si
    0.51
     risulta
    0.51
     Si
    0.48
     arriva
    0.48
    Activations Density 0.006%

    No Known Activations