© 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. 182364
    Prev
    Next
    INDEX
    Explanations

    situation, general, say, away, risk

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

    Instrumental Convergence

    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
    aldo
    0.55
    ecos
    0.53
    𝓲
    0.52
     ग्रहों
    0.52
    ênio
    0.51
    ę
    0.49
    ciò
    0.48
    लिंग
    0.48
    verters
    0.48
    ando
    0.47
    POSITIVE LOGITS
     cr
    0.52
     leurs
    0.46
     CR
    0.45
     r
    0.44
     wrap
    0.43
     Jacob
    0.43
     clue
    0.42
     ν
    0.42
     ink
    0.42
     Forks
    0.42
    Activations Density 0.001%

    No Known Activations