© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10660
    Prev
    Next
    INDEX
    Explanations

    Tumblr

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

    dominance and control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lol
    0.47
     awesome
    0.46
     lol
    0.46
     reviewer
    0.46
     OMG
    0.46
     sConfig
    0.46
     reviewers
    0.44
    😄
    0.44
     :/
    0.44
    ^_^
    0.43
    POSITIVE LOGITS
    tumblr
    0.50
     canonically
    0.48
     Tumblr
    0.47
    aesthetic
    0.46
     tumbler
    0.46
    Canon
    0.45
    Fuck
    0.44
    Tum
    0.44
    𓂃
    0.44
    cpf
    0.43
    Activations Density 0.035%

    No Known Activations