© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1686
    Prev
    Next
    INDEX
    Explanations

    conversational scenarios or explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
    ről
    0.93
    橿
    0.89
     Frum
    0.89
     eind
    0.86
     Kisi
    0.83
    Ordine
    0.82
    éről
    0.81
    ชี
    0.80
    恆
    0.79
    زور
    0.77
    POSITIVE LOGITS
     Louie
    1.40
    \;\
    1.31
     smoothie
    1.25
     microsomal
    1.23
     cook
    1.21
     thighs
    1.19
     noodles
    1.19
     Loeb
    1.19
     puree
    1.18
     chile
    1.17
    Activations Density 0.000%

    No Known Activations