© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 25244
    Prev
    Next
    INDEX
    Explanations

    the [place/noun]

    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_262k_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
     its
    0.43
     our
    0.40
     Generate
    0.39
     your
    0.38
     YOUR
    0.38
     S
    0.37
     milik
    0.37
     O
    0.37
     Get
    0.36
     Template
    0.36
    POSITIVE LOGITS
     room
    0.45
    房间
    0.40
     distraught
    0.40
     hallway
    0.40
    кистон
    0.39
     pomiesz
    0.39
     courthouse
    0.39
     bathroom
    0.38
    bedrooms
    0.38
     foyer
    0.38
    Activations Density 0.013%

    No Known Activations