© 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. 34049
    Prev
    Next
    INDEX
    Explanations

    equivalence and interchangeability

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

    equivalence and interchangeability

    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
    र्नर
    0.38
    ર્ચ
    0.38
     først
    0.36
     klart
    0.36
    ాలకు
    0.36
     supernatant
    0.36
     först
    0.36
    睺
    0.36
    ात
    0.36
    teacher
    0.36
    POSITIVE LOGITS
     interchangeable
    0.88
     equivalence
    0.86
     indist
    0.84
     interchangeably
    0.83
    equivalence
    0.83
     equival
    0.82
    equival
    0.79
     equivalents
    0.76
     Equivalent
    0.76
    Equivalent
    0.75
    Activations Density 0.039%

    No Known Activations