© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 39886
    Prev
    Next
    INDEX
    Explanations

    abstract and 'ab' words

    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
    havior
    0.39
    daftar
    0.38
     nuclei
    0.37
    mäßig
    0.37
     Defects
    0.37
    iagn
    0.37
    rieron
    0.37
    ⩾
    0.37
    ieno
    0.36
    ozen
    0.36
    POSITIVE LOGITS
     drawRight
    0.44
    あ
    0.44
    Straw
    0.41
     오른쪽
    0.40
    ቕ
    0.40
    बान
    0.39
    萸
    0.39
    Ⴉ
    0.39
     წ
    0.39
    Scala
    0.38
    Activations Density 0.007%

    No Known Activations