© 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. 223426
    Prev
    Next
    INDEX
    Explanations

    word followed by related word

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

    logical next step

    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
    })$
    0.49
     landlords
    0.48
    =',
    0.48
    ',
    0.47
    を行い
    0.46
     landlord
    0.46
    仏
    0.46
     reali
    0.46
    טה
    0.44
    })
    0.44
    POSITIVE LOGITS
     आहेत
    0.45
     স্পর্শ
    0.45
     ቅር
    0.44
     पाइप
    0.43
     जादू
    0.43
     แบ่ง
    0.43
    Jazz
    0.42
     Sparse
    0.42
     PhoneNumber
    0.41
     τῶν
    0.40
    Activations Density 0.001%

    No Known Activations