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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118949
    Prev
    Next
    INDEX
    Explanations

    is/are followed by a descriptor

    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
    これは
    -1.09
     hinauf
    -1.05
     perché
    -1.02
    それが
    -1.00
     possessor
    -0.97
    iële
    -0.96
     anstatt
    -0.96
    meniz
    -0.95
    PLEASE
    -0.94
     tą
    -0.93
    POSITIVE LOGITS
     not
    1.80
     like
    1.52
     what
    1.45
     always
    1.43
     never
    1.25
     our
    1.21
     a
    1.20
     merely
    1.15
     just
    1.13
     meant
    1.12
    Activations Density 0.047%

    No Known Activations