© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 61441
    Prev
    Next
    INDEX
    Explanations

    end of sentence/phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    తున్నాయి
    0.43
    Barcelona
    0.41
    >;</
    0.41
    Death
    0.41
     অবত
    0.40
     pü
    0.40
     DEATH
    0.39
     calcS
    0.39
     maiden
    0.39
    ريقيا
    0.38
    POSITIVE LOGITS
     immoral
    0.41
     Unable
    0.36
     girly
    0.34
    憋
    0.34
     Teach
    0.34
     کبھی
    0.34
    obeb
    0.34
     Technologies
    0.34
     desist
    0.34
    adoop
    0.33
    Activations Density 0.005%

    No Known Activations