© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3424
    Prev
    Next
    INDEX
    Explanations

    states or qualities

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

    abstract concepts and states

    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_31_width_262k_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
    five
    0.54
     partly
    0.51
     छह
    0.50
    six
    0.49
    enable
    0.49
     '../
    0.47
    },
    0.46
    த்
    0.46
     पाँच
    0.45
    create
    0.45
    POSITIVE LOGITS
    窜
    0.59
     unglaublich
    0.54
    Fuck
    0.53
     thằng
    0.53
     lmao
    0.52
    Oath
    0.52
    Droite
    0.52
    我认为
    0.51
    🤙
    0.50
     alakalı
    0.49
    Activations Density 0.363%

    No Known Activations