© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 38168
    Prev
    Next
    INDEX
    Explanations

    official applications and procedures

    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
    ₅
    -0.98
    acebook
    -0.94
     καὶ
    -0.93
    derry
    -0.90
    zación
    -0.90
     그림
    -0.89
     ادبی
    -0.85
     ἐκ
    -0.85
    цах
    -0.84
    romeda
    -0.84
    POSITIVE LOGITS
     applicants
    1.66
     processing
    1.63
     bureaucratic
    1.58
     procedure
    1.48
     trámite
    1.41
    processing
    1.40
    申请
    1.39
     process
    1.38
     paperwork
    1.38
     applicant
    1.35
    Activations Density 0.045%

    No Known Activations