© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 50627
    Prev
    Next
    INDEX
    Explanations

    worthlessness weakness

    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
    ।
    0.47
    Sail
    0.44
    {
    0.44
     était
    0.42
    Roof
    0.42
    K
    0.42
     startet
    0.42
    L
    0.42
    }$.
    0.42
     roof
    0.42
    POSITIVE LOGITS
    づ
    0.44
    ешь
    0.43
     سلمان
    0.43
     TMZ
    0.41
    欲望
    0.41
    ેચ્છ
    0.41
    ༤
    0.41
     സു
    0.40
    том
    0.39
    ذی
    0.39
    Activations Density 0.036%

    No Known Activations