© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 9748
    Prev
    Next
    INDEX
    Explanations

    God's blessings and warnings

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

    The neuron flags first‐person future‐tense commitments—i.e. “I will …” statements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     blessures
    -1.22
    jusqu
    -1.15
    Música
    -1.09
    视为
    -1.07
    咂
    -1.04
    ranging
    -1.02
    ujesz
    -1.01
    mogen
    -1.01
    decided
    -1.00
    Política
    -0.98
    POSITIVE LOGITS
     similar
    1.45
     actions
    1.33
     people
    1.28
     not
    1.23
     and
    1.23
     what
    1.18
     happy
    1.17
     made
    1.16
     good
    1.13
    でしたね
    1.12
    Activations Density 0.030%

    No Known Activations