© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78614
    Prev
    Next
    INDEX
    Explanations

    aimed at or targeting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odiment
    -0.90
    خذ
    -0.82
    ذة
    -0.82
    iltà
    -0.79
    lorem
    -0.77
    Opus
    -0.77
     découvre
    -0.74
    ิ้น
    -0.73
    を決
    -0.72
    が決
    -0.71
    POSITIVE LOGITS
     aimed
    4.22
     targeted
    3.70
     targeting
    3.69
     catering
    3.52
     target
    3.17
    targeted
    3.09
     cater
    3.08
     geared
    3.08
     catered
    3.06
     caters
    3.06
    Activations Density 0.214%

    No Known Activations