© 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. 80437
    Prev
    Next
    INDEX
    Explanations

    we acquired, we had

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

    preserving relevant information

    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
    บ
    0.48
    Africa
    0.47
     ऑफ़
    0.46
     Reiki
    0.46
     Skills
    0.45
     Macbook
    0.45
     বিশ্বকাপ
    0.45
     SK
    0.43
    Arsenal
    0.43
    Gamepad
    0.43
    POSITIVE LOGITS
     superficie
    0.51
     deleterious
    0.46
     incipient
    0.44
     fenders
    0.44
     sublattice
    0.43
    ⟋
    0.43
     recientes
    0.42
     surface
    0.42
     terl
    0.42
     precipitates
    0.42
    Activations Density 0.004%

    No Known Activations