© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 32803
    Prev
    Next
    INDEX
    Explanations

    tickets at the door

    np_acts-logits-general · gemini-2.5-flash-lite

    code constructs like `()`, `[]`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     necesitamos
    0.50
    ቝ
    0.50
    ियन
    0.47
    बहन
    0.47
     cosecha
    0.46
    ज्ञापन
    0.46
    來說
    0.44
    तुम्हारा
    0.44
     جوړونکو
    0.44
    ठीक
    0.43
    POSITIVE LOGITS
    /
    0.61
     and
    0.54
    ,
    0.50
     và
    0.48
      
    0.48
     &
    0.46
     vs
    0.45
    &
    0.45
     Entry
    0.44
    opcode
    0.44
    Activations Density 0.000%

    No Known Activations