Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 18761
    Prev
    Next
    INDEX
    Explanations

    SAMHSA National Helpline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_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
    擬
    0.41
    False
    0.40
    oisin
    0.40
    Finn
    0.38
    нет
    0.38
    τυ
    0.37
    arrayOf
    0.37
    issory
    0.37
    ara
    0.36
    ::-
    0.35
    POSITIVE LOGITS
     hotline
    1.74
     Hotline
    1.53
     helpline
    1.50
     Helpline
    1.34
     हेल्पलाइन
    1.21
     toll
    1.10
     hot
    1.06
     line
    1.01
     HOT
    1.00
     telephone
    0.98
    Activations Density 0.029%

    No Known Activations