© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 36274
    Prev
    Next
    INDEX
    Explanations

    firewall configuration

    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_31_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
     =)
    0.76
     ;)
    0.75
    Alongside
    0.57
     :)
    0.56
    Whilst
    0.55
    Alright
    0.54
     aswell
    0.54
     również
    0.54
     unsurprisingly
    0.53
     Помимо
    0.52
    POSITIVE LOGITS
    いろいろ
    0.75
    ⁦
    0.69
     kuchh
    0.66
     Covid
    0.66
     ২০২৩
    0.65
    令和
    0.64
    新冠
    0.64
    Covid
    0.64
     appreciably
    0.64
     marvelous
    0.64
    Activations Density 0.032%

    No Known Activations