© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1411
    Prev
    Next
    INDEX
    Explanations

    Camarena spelling variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     чудо
    0.95
    𝗲
    0.93
     及び
    0.90
    पौ
    0.90
    𝘂
    0.89
    ção
    0.89
     não
    0.89
     Pét
    0.89
    ᅣ
    0.88
     nonostante
    0.88
    POSITIVE LOGITS
     aggressive
    0.84
    aggressive
    0.79
    heavy
    0.77
     tendency
    0.76
     dominant
    0.76
     delicate
    0.75
     heavy
    0.73
     them
    0.72
     penetrating
    0.70
     blockage
    0.69
    Activations Density 0.000%

    No Known Activations