© 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. 78153
    Prev
    Next
    INDEX
    Explanations

    online forums and websites

    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
     erlauben
    -0.94
    ဆ
    -0.81
    图像
    -0.71
    roglo
    -0.69
     przeci
    -0.68
     сковоро
    -0.68
     pray
    -0.68
    曲线
    -0.67
     версии
    -0.67
    aglio
    -0.67
    POSITIVE LOGITS
     OBD
    0.76
     vacated
    0.76
     boards
    0.74
    inhabited
    0.73
     vacu
    0.73
    研究院
    0.73
     SVN
    0.72
    Empire
    0.72
     Empire
    0.71
    UCHAR
    0.71
    Activations Density 0.052%

    No Known Activations